From 8c2178b570d75fe56ca270878254fb75c8257538 Mon Sep 17 00:00:00 2001 From: github-actions <41898282+github-actions[bot]@users.noreply.github.com> Date: Sat, 14 Dec 2024 11:17:34 +0000 Subject: [PATCH] auto: update csv outputs to version 2024.12.14 --- csv/huggingface_v2.csv | 218 ++++++++++++++++++++--------------------- csv/merged.csv | 24 ++--- 2 files changed, 121 insertions(+), 121 deletions(-) diff --git a/csv/huggingface_v2.csv b/csv/huggingface_v2.csv index bfd5266..8b67622 100644 --- a/csv/huggingface_v2.csv +++ b/csv/huggingface_v2.csv @@ -27,7 +27,7 @@ id,model_name,model_sha,model_precision,model_type,model_weight_type,model_archi 3rd-Degree-Burn/Llama-3.1-8B-Squareroot-v1_float16_09339d9c3b118ae3c6e7beab8b84347471990988_True,3rd-Degree-Burn/Llama-3.1-8B-Squareroot-v1,09339d9c3b118ae3c6e7beab8b84347471990988,float16,basemergesandmoerges,Original,LlamaForCausalLM,7.59736191936822,TRUE,IFEval,0.289238110435866,28.9238110435866,BBH,0.334277031192513,6.51514472598274,MATH Level 5,0.0619335347432024,6.19335347432024,GPQA,0.255872483221477,0.782997762863532,MUSR,0.3340625,1.7578125,MMLU-PRO,0.112699468085106,1.41105200945626,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-11-10,0,Removed,"",0,8.03,0.772749272395982 3rd-Degree-Burn/Llama-Squared-8B_bfloat16_f30737e92b3a3fa0ef2a3f3ade487cc94ad34400_True,3rd-Degree-Burn/Llama-Squared-8B,f30737e92b3a3fa0ef2a3f3ade487cc94ad34400,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,12.2335443250511,TRUE,IFEval,0.275524497222924,27.5524497222924,BBH,0.443102568386835,21.2771031901068,MATH Level 5,0.0453172205438067,4.53172205438067,GPQA,0.271812080536913,2.9082774049217,MUSR,0.308947916666667,1.95182291666667,MMLU-PRO,0.236619015957447,15.1798906619385,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-10-08,0,Removed,"",0,8.03,1.01111152474142 4season/final_model_test_v2_bfloat16_cf690c35d9cf0b0b6bf034fa16dbf88c56fe861c_False,4season/final_model_test_v2,cf690c35d9cf0b0b6bf034fa16dbf88c56fe861c,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,21.9155401795957,FALSE,IFEval,0.319113286080932,31.9113286080932,BBH,0.634204978329502,47.4106701369064,MATH Level 5,0.013595166163142,1.3595166163142,GPQA,0.327181208053691,10.2908277404922,MUSR,0.431447916666667,12.4309895833333,MMLU-PRO,0.352809175531915,28.089908392435,TRUE,FALSE,FALSE,FALSE,FALSE,2024-05-20,2024-06-27,0,4season/final_model_test_v2,apache-2.0,0,21.421,1.0810383598407 -AALF/FuseChat-Llama-3.1-8B-Instruct-preview_bfloat16_f740497979293c90fa1cfaa7c446016e107cc2c1_True,AALF/FuseChat-Llama-3.1-8B-Instruct-preview,f740497979293c90fa1cfaa7c446016e107cc2c1,bfloat16,chatmodels,Original,LlamaForCausalLM,25.6103675067756,TRUE,IFEval,0.718957920539724,71.8957920539723,BBH,0.51198878983499,30.8480652162296,MATH Level 5,0.0702416918429003,7.02416918429003,GPQA,0.305369127516779,7.38255033557047,MUSR,0.382,6.15000000000001,MMLU-PRO,0.373254654255319,30.361628250591,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-20,2024-11-20,0,AALF/FuseChat-Llama-3.1-8B-Instruct-preview,"",1,8.03,0.68861912808304 +AALF/FuseChat-Llama-3.1-8B-Instruct-preview_bfloat16_f740497979293c90fa1cfaa7c446016e107cc2c1_True,AALF/FuseChat-Llama-3.1-8B-Instruct-preview,f740497979293c90fa1cfaa7c446016e107cc2c1,bfloat16,chatmodels,Original,LlamaForCausalLM,25.6103675067756,TRUE,IFEval,0.718957920539724,71.8957920539723,BBH,0.51198878983499,30.8480652162296,MATH Level 5,0.0702416918429003,7.02416918429003,GPQA,0.305369127516779,7.38255033557047,MUSR,0.382,6.15000000000001,MMLU-PRO,0.373254654255319,30.361628250591,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-20,2024-11-20,0,AALF/FuseChat-Llama-3.1-8B-Instruct-preview,"",4,8.03,0.68861912808304 AALF/FuseChat-Llama-3.1-8B-SFT-preview_bfloat16_601f2b8c448acc5686656d3979ed732ce050b827_True,AALF/FuseChat-Llama-3.1-8B-SFT-preview,601f2b8c448acc5686656d3979ed732ce050b827,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,27.3748389276178,TRUE,IFEval,0.728050461663941,72.8050461663941,BBH,0.524030313044523,32.536781563153,MATH Level 5,0.11404833836858,11.404833836858,GPQA,0.304530201342282,7.27069351230425,MUSR,0.402,9.75,MMLU-PRO,0.374335106382979,30.4816784869976,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-20,2024-11-21,0,AALF/FuseChat-Llama-3.1-8B-SFT-preview,"",0,8.03,0.684307538380291 AALF/gemma-2-27b-it-SimPO-37K_bfloat16_27f15219df2000a16955c9403c3f38b5f3413b3d_True,AALF/gemma-2-27b-it-SimPO-37K,27f15219df2000a16955c9403c3f38b5f3413b3d,bfloat16,chatmodels,Original,Gemma2ForCausalLM,9.29807939486237,TRUE,IFEval,0.240652579599906,24.0652579599906,BBH,0.391134391795253,15.3078809719543,MATH Level 5,0,0,GPQA,0.280201342281879,4.0268456375839,MUSR,0.348760416666667,1.59505208333333,MMLU-PRO,0.197140957446809,10.7934397163121,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-13,2024-09-05,2,google/gemma-2-27b,gemma,18,27.227,9.9977216254124 AALF/gemma-2-27b-it-SimPO-37K-100steps_bfloat16_d5cbf18b2eb90b77f5ddbb74cfcaeedfa692c90c_True,AALF/gemma-2-27b-it-SimPO-37K-100steps,d5cbf18b2eb90b77f5ddbb74cfcaeedfa692c90c,bfloat16,chatmodels,Original,Gemma2ForCausalLM,9.89433609242818,TRUE,IFEval,0.25676427434762,25.676427434762,BBH,0.39308230769885,15.2610783228471,MATH Level 5,0,0,GPQA,0.288590604026846,5.14541387024609,MUSR,0.332916666666667,0.78125,MMLU-PRO,0.212516622340426,12.5018469267139,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-13,2024-09-21,2,google/gemma-2-27b,gemma,11,27.227,9.85673547469955 @@ -41,7 +41,7 @@ AI-Sweden-Models/Llama-3-8B-instruct_bfloat16_4e1c955228bdb4d69c1c4560e8d5872312 AI-Sweden-Models/gpt-sw3-40b_float16_1af27994df1287a7fac1b10d60e40ca43a22a385_False,AI-Sweden-Models/gpt-sw3-40b,1af27994df1287a7fac1b10d60e40ca43a22a385,float16,pretrained,Original,GPT2LMHeadModel,4.73443320029372,FALSE,IFEval,0.147029880716499,14.7029880716499,BBH,0.326774470295765,6.89493405079658,MATH Level 5,0.00906344410876133,0.906344410876133,GPQA,0.23489932885906,0,MUSR,0.363239583333333,2.83828125,MMLU-PRO,0.127576462765957,3.06405141843972,TRUE,FALSE,FALSE,FALSE,FALSE,2023-02-22,2024-06-26,0,AI-Sweden-Models/gpt-sw3-40b,other,10,39.927,2.95981936505708 AbacusResearch/Jallabi-34B_float16_f65696da4ed82c9a20e94b200d9dccffa07af682_False,AbacusResearch/Jallabi-34B,f65696da4ed82c9a20e94b200d9dccffa07af682,float16,basemergesandmoerges,Original,LlamaForCausalLM,25.9720839348152,FALSE,IFEval,0.352860410377798,35.2860410377798,BBH,0.602338060319627,43.6157649871951,MATH Level 5,0.0392749244712991,3.92749244712991,GPQA,0.338926174496644,11.8568232662192,MUSR,0.482177083333333,20.2388020833333,MMLU-PRO,0.468168218085106,40.907579787234,TRUE,FALSE,FALSE,FALSE,FALSE,2024-03-01,2024-06-27,0,AbacusResearch/Jallabi-34B,apache-2.0,2,34.389,3.28649233978473 Alibaba-NLP/gte-Qwen2-7B-instruct_bfloat16_e26182b2122f4435e8b3ebecbf363990f409b45b_True,Alibaba-NLP/gte-Qwen2-7B-instruct,e26182b2122f4435e8b3ebecbf363990f409b45b,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,13.4061800867193,TRUE,IFEval,0.225540454881936,22.5540454881936,BBH,0.449514499081847,21.9254824856624,MATH Level 5,0.0385196374622357,3.85196374622357,GPQA,0.24496644295302,0,MUSR,0.355854166666667,6.31510416666667,MMLU-PRO,0.332114361702128,25.7904846335697,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-15,2024-08-05,0,Alibaba-NLP/gte-Qwen2-7B-instruct,apache-2.0,227,7.613,2.17211334857993 -ArliAI/ArliAI-RPMax-12B-v1.1_bfloat16_645db1cf8ad952eb57854a133e8e15303b898b04_True,ArliAI/ArliAI-RPMax-12B-v1.1,645db1cf8ad952eb57854a133e8e15303b898b04,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,20.8126943934558,TRUE,IFEval,0.534885215672194,53.4885215672194,BBH,0.475181760840119,24.8090633179328,MATH Level 5,0.102719033232628,10.2719033232628,GPQA,0.281879194630873,4.25055928411633,MUSR,0.36184375,5.56380208333334,MMLU-PRO,0.33843085106383,26.49231678487,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-31,2024-09-05,0,ArliAI/ArliAI-RPMax-12B-v1.1,apache-2.0,41,12.248,1.83340230532795 +ArliAI/ArliAI-RPMax-12B-v1.1_bfloat16_645db1cf8ad952eb57854a133e8e15303b898b04_True,ArliAI/ArliAI-RPMax-12B-v1.1,645db1cf8ad952eb57854a133e8e15303b898b04,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,20.8126943934558,TRUE,IFEval,0.534885215672194,53.4885215672194,BBH,0.475181760840119,24.8090633179328,MATH Level 5,0.102719033232628,10.2719033232628,GPQA,0.281879194630873,4.25055928411633,MUSR,0.36184375,5.56380208333334,MMLU-PRO,0.33843085106383,26.49231678487,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-31,2024-09-05,0,ArliAI/ArliAI-RPMax-12B-v1.1,apache-2.0,42,12.248,1.83340230532795 ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1_bfloat16_540bd352e59c63900af91b95a932b33aaee70c76_True,ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1,540bd352e59c63900af91b95a932b33aaee70c76,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,23.9169670346878,TRUE,IFEval,0.635901629897561,63.5901629897561,BBH,0.501561345603908,28.7870140994428,MATH Level 5,0.129909365558912,12.9909365558912,GPQA,0.283557046979866,4.47427293064877,MUSR,0.3576875,5.3109375,MMLU-PRO,0.355136303191489,28.3484781323877,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-23,2024-09-19,0,ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1,llama3,29,8.03,0.892744758538456 Artples/L-MChat-7b_bfloat16_e10137f5cbfc1b73068d6473e4a87241cca0b3f4_True,Artples/L-MChat-7b,e10137f5cbfc1b73068d6473e4a87241cca0b3f4,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,21.2259053274249,TRUE,IFEval,0.529664623199777,52.9664623199777,BBH,0.460033016746794,24.2015573888133,MATH Level 5,0.0913897280966767,9.13897280966767,GPQA,0.305369127516779,7.38255033557047,MUSR,0.402864583333333,8.12473958333333,MMLU-PRO,0.329870345744681,25.5411495271868,TRUE,TRUE,FALSE,FALSE,FALSE,2024-04-02,2024-07-07,1,Artples/L-MChat-7b (Merge),apache-2.0,2,7.242,0.592226185702351 Artples/L-MChat-Small_bfloat16_52484c277f6062c12dc6d6b6397ee0d0c21b0126_True,Artples/L-MChat-Small,52484c277f6062c12dc6d6b6397ee0d0c21b0126,bfloat16,basemergesandmoerges,Original,PhiForCausalLM,14.8914488285507,TRUE,IFEval,0.328705612220021,32.8705612220021,BBH,0.482256276652573,26.8565155000314,MATH Level 5,0.0173716012084592,1.73716012084592,GPQA,0.26761744966443,2.3489932885906,MUSR,0.36959375,9.26588541666666,MMLU-PRO,0.246426196808511,16.2695774231678,TRUE,TRUE,FALSE,FALSE,FALSE,2024-04-11,2024-07-07,1,Artples/L-MChat-Small (Merge),mit,1,2.78,0.465510595183882 @@ -77,7 +77,7 @@ BEE-spoke-data/tFINE-900m-e16-d32-flan_bfloat16_d9ffec9798402d13d8f2c56ec3de3ad0 BEE-spoke-data/tFINE-900m-e16-d32-flan-infinity-instruct-7m-T2T_en-1024_bfloat16_b1e2f12f5224be9f7da0cb5ff30e1bbb3f10f6ca_False,BEE-spoke-data/tFINE-900m-e16-d32-flan-infinity-instruct-7m-T2T_en-1024,b1e2f12f5224be9f7da0cb5ff30e1bbb3f10f6ca,bfloat16,fine-tunedondomain-specificdatasets,Original,T5ForConditionalGeneration,5.82365268524396,FALSE,IFEval,0.13206735905176,13.206735905176,BBH,0.313778630449759,4.737018282628,MATH Level 5,0,0,GPQA,0.254194630872483,0.559284116331097,MUSR,0.439270833333333,13.8088541666667,MMLU-PRO,0.123670212765957,2.63002364066194,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-10,2024-09-14,2,pszemraj/tFINE-900m-e16-d32-1024ctx,apache-2.0,0,0.887,2.60060794811745 BEE-spoke-data/tFINE-900m-e16-d32-instruct_2e_bfloat16_4c626138c9f4e0c3eafe74b2755eb89334c7ca59_False,BEE-spoke-data/tFINE-900m-e16-d32-instruct_2e,4c626138c9f4e0c3eafe74b2755eb89334c7ca59,bfloat16,fine-tunedondomain-specificdatasets,Original,T5ForConditionalGeneration,5.68155232668207,FALSE,IFEval,0.140285553442643,14.0285553442643,BBH,0.31345674638809,5.01307033590438,MATH Level 5,0,0,GPQA,0.259228187919463,1.23042505592841,MUSR,0.420697916666667,11.1872395833333,MMLU-PRO,0.123670212765957,2.63002364066194,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-17,2024-09-22,3,pszemraj/tFINE-900m-e16-d32-1024ctx,apache-2.0,0,0.887,2.51661868035774 BEE-spoke-data/tFINE-900m-instruct-orpo_bfloat16_e0a21c79bac74442252d36e2c01403afa3f0971b_True,BEE-spoke-data/tFINE-900m-instruct-orpo,e0a21c79bac74442252d36e2c01403afa3f0971b,bfloat16,chatmodels,Original,T5ForConditionalGeneration,3.43195747178208,TRUE,IFEval,0.132991573469505,13.2991573469505,BBH,0.302209337670451,3.26730057793177,MATH Level 5,0,0,GPQA,0.259228187919463,1.23042505592841,MUSR,0.340854166666667,1.10677083333333,MMLU-PRO,0.115192819148936,1.68809101654846,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-22,2024-09-23,0,BEE-spoke-data/tFINE-900m-instruct-orpo,apache-2.0,0,0.887,2.57496193202933 -BSC-LT/salamandra-7b_float16_bf30739316ceac4b624583a27ec96dfc401179e8_False,BSC-LT/salamandra-7b,bf30739316ceac4b624583a27ec96dfc401179e8,float16,pretrained,Original,LlamaForCausalLM,5.64197086025683,FALSE,IFEval,0.136738298824896,13.6738298824896,BBH,0.351661220988598,10.1574219905203,MATH Level 5,0,0,GPQA,0.27013422818792,2.68456375838927,MUSR,0.35009375,1.86171875,MMLU-PRO,0.149268617021277,5.47429078014184,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-30,2024-11-22,0,BSC-LT/salamandra-7b,apache-2.0,13,7.768,0.189288664141019 +BSC-LT/salamandra-7b_float16_bf30739316ceac4b624583a27ec96dfc401179e8_False,BSC-LT/salamandra-7b,bf30739316ceac4b624583a27ec96dfc401179e8,float16,pretrained,Original,LlamaForCausalLM,5.64197086025683,FALSE,IFEval,0.136738298824896,13.6738298824896,BBH,0.351661220988598,10.1574219905203,MATH Level 5,0,0,GPQA,0.27013422818792,2.68456375838927,MUSR,0.35009375,1.86171875,MMLU-PRO,0.149268617021277,5.47429078014184,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-30,2024-11-22,0,BSC-LT/salamandra-7b,apache-2.0,14,7.768,0.189288664141019 BSC-LT/salamandra-7b-instruct_float16_77ddccbc7d9f9ffd55a8535365e8eebc493ccb8e_True,BSC-LT/salamandra-7b-instruct,77ddccbc7d9f9ffd55a8535365e8eebc493ccb8e,float16,pretrained,Original,LlamaForCausalLM,10.080538762462,TRUE,IFEval,0.245074180950988,24.5074180950988,BBH,0.385132429008096,14.6881285457313,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.264261744966443,1.90156599552573,MUSR,0.4134375,10.2130208333333,MMLU-PRO,0.180518617021277,8.94651300236406,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-30,2024-11-22,1,BSC-LT/salamandra-7b-instruct (Merge),apache-2.0,33,7.768,1.14750408633701 Ba2han/Llama-Phi-3_DoRA_bfloat16_36f99064a7be8ba475c2ee5c5424e95c263ccb87_True,Ba2han/Llama-Phi-3_DoRA,36f99064a7be8ba475c2ee5c5424e95c263ccb87,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,25.3188375993417,TRUE,IFEval,0.513053143437191,51.3053143437191,BBH,0.551455825902919,37.2491641807927,MATH Level 5,0.112537764350453,11.2537764350453,GPQA,0.326342281879195,10.1789709172259,MUSR,0.406927083333333,9.53255208333334,MMLU-PRO,0.391539228723404,32.3932476359338,TRUE,FALSE,FALSE,FALSE,FALSE,2024-05-15,2024-06-26,0,Ba2han/Llama-Phi-3_DoRA,mit,6,3.821,0.533136350019229 BenevolenceMessiah/Qwen2.5-72B-2x-Instruct-TIES-v1.0_bfloat16_459891ec78c9bbed2836a8bba706e1707db10231_True,BenevolenceMessiah/Qwen2.5-72B-2x-Instruct-TIES-v1.0,459891ec78c9bbed2836a8bba706e1707db10231,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,34.1857491389051,TRUE,IFEval,0.547349920433339,54.7349920433339,BBH,0.727311411382245,61.9114945306048,MATH Level 5,0.0936555891238671,9.36555891238671,GPQA,0.36744966442953,15.6599552572707,MUSR,0.420666666666667,12.0166666666667,MMLU-PRO,0.562832446808511,51.4258274231679,FALSE,FALSE,FALSE,FALSE,FALSE,2024-11-11,2024-11-24,1,BenevolenceMessiah/Qwen2.5-72B-2x-Instruct-TIES-v1.0 (Merge),"",0,72.7,17.3508918531852 @@ -110,9 +110,9 @@ ClaudioItaly/Evolutionstory-7B-v2.2_bfloat16_9f838721d24a5195bed59a5ed8d9af536f7 ClaudioItaly/intelligence-cod-rag-7b-v3_bfloat16_2b21473c8a086f8d0c54b82c3454bf5499cdde3a_True,ClaudioItaly/intelligence-cod-rag-7b-v3,2b21473c8a086f8d0c54b82c3454bf5499cdde3a,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,27.1290106554156,TRUE,IFEval,0.689782000647172,68.9782000647172,BBH,0.536633971883911,34.7761585394944,MATH Level 5,0.0981873111782477,9.81873111782477,GPQA,0.272651006711409,3.02013422818792,MUSR,0.415270833333333,10.6755208333333,MMLU-PRO,0.419547872340426,35.5053191489362,TRUE,TRUE,FALSE,FALSE,FALSE,2024-11-29,2024-12-02,1,ClaudioItaly/intelligence-cod-rag-7b-v3 (Merge),mit,0,7.616,0.660472333052409 CohereForAI/aya-23-35B_float16_31d6fd858f20539a55401c7ad913086f54d9ca2c_True,CohereForAI/aya-23-35B,31d6fd858f20539a55401c7ad913086f54d9ca2c,float16,chatmodels,Original,CohereForCausalLM,24.6798797460333,TRUE,IFEval,0.646193211789164,64.6193211789164,BBH,0.539955145073127,34.8583604677546,MATH Level 5,0.0302114803625378,3.02114803625378,GPQA,0.294463087248322,5.92841163310962,MUSR,0.430989583333333,13.4736979166667,MMLU-PRO,0.335605053191489,26.1783392434988,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-19,2024-06-12,0,CohereForAI/aya-23-35B,cc-by-nc-4.0,268,34.981,16.9853170194836 CohereForAI/aya-23-8B_float16_ec151d218a24031eb039d92fb83d10445427efc9_True,CohereForAI/aya-23-8B,ec151d218a24031eb039d92fb83d10445427efc9,float16,chatmodels,Original,CohereForCausalLM,15.998395031351,TRUE,IFEval,0.469888783982057,46.9888783982057,BBH,0.429616151922031,20.2037606467394,MATH Level 5,0.0158610271903323,1.58610271903323,GPQA,0.284395973154362,4.58612975391499,MUSR,0.3940625,8.42447916666666,MMLU-PRO,0.227809175531915,14.2010195035461,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-19,2024-06-12,0,CohereForAI/aya-23-8B,cc-by-nc-4.0,396,8.028,1.19517208132096 -CohereForAI/aya-expanse-32b_float16_08b69cfa4240e2009c80ad304f000b491d1b8c38_True,CohereForAI/aya-expanse-32b,08b69cfa4240e2009c80ad304f000b491d1b8c38,float16,chatmodels,Original,CohereForCausalLM,29.3912190893162,TRUE,IFEval,0.730173716849072,73.0173716849072,BBH,0.564867009921211,38.7096114330142,MATH Level 5,0.13368580060423,13.368580060423,GPQA,0.325503355704698,10.0671140939597,MUSR,0.387270833333333,6.40885416666667,MMLU-PRO,0.41298204787234,34.7757830969267,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-23,2024-10-24,0,CohereForAI/aya-expanse-32b,cc-by-nc-4.0,187,32.296,5.5177350999101 +CohereForAI/aya-expanse-32b_float16_08b69cfa4240e2009c80ad304f000b491d1b8c38_True,CohereForAI/aya-expanse-32b,08b69cfa4240e2009c80ad304f000b491d1b8c38,float16,chatmodels,Original,CohereForCausalLM,29.3912190893162,TRUE,IFEval,0.730173716849072,73.0173716849072,BBH,0.564867009921211,38.7096114330142,MATH Level 5,0.13368580060423,13.368580060423,GPQA,0.325503355704698,10.0671140939597,MUSR,0.387270833333333,6.40885416666667,MMLU-PRO,0.41298204787234,34.7757830969267,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-23,2024-10-24,0,CohereForAI/aya-expanse-32b,cc-by-nc-4.0,188,32.296,5.5177350999101 CohereForAI/aya-expanse-8b_float16_b9848575c8731981dfcf2e1f3bfbcb917a2e585d_True,CohereForAI/aya-expanse-8b,b9848575c8731981dfcf2e1f3bfbcb917a2e585d,float16,chatmodels,Original,CohereForCausalLM,22.1422232448213,TRUE,IFEval,0.63585176221315,63.585176221315,BBH,0.497720305573641,28.5234825042885,MATH Level 5,0.0702416918429003,7.02416918429003,GPQA,0.302852348993289,7.04697986577182,MUSR,0.372885416666667,4.41067708333333,MMLU-PRO,0.300365691489362,22.2628546099291,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-23,2024-10-24,0,CohereForAI/aya-expanse-8b,cc-by-nc-4.0,304,8.028,1.1696890688757 -CohereForAI/c4ai-command-r-plus_float16_fa1bd7fb1572ceb861bbbbecfa8af83b29fa8cca_True,CohereForAI/c4ai-command-r-plus,fa1bd7fb1572ceb861bbbbecfa8af83b29fa8cca,float16,chatmodels,Original,CohereForCausalLM,30.961246846254,TRUE,IFEval,0.766418658049531,76.6418658049531,BBH,0.581542357407793,39.9199542314318,MATH Level 5,0.081570996978852,8.1570996978852,GPQA,0.305369127516779,7.38255033557047,MUSR,0.48071875,20.4231770833333,MMLU-PRO,0.399185505319149,33.2428339243499,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-03,2024-06-13,0,CohereForAI/c4ai-command-r-plus,cc-by-nc-4.0,1694,103.811,28.6315317116708 +CohereForAI/c4ai-command-r-plus_float16_fa1bd7fb1572ceb861bbbbecfa8af83b29fa8cca_True,CohereForAI/c4ai-command-r-plus,fa1bd7fb1572ceb861bbbbecfa8af83b29fa8cca,float16,chatmodels,Original,CohereForCausalLM,30.961246846254,TRUE,IFEval,0.766418658049531,76.6418658049531,BBH,0.581542357407793,39.9199542314318,MATH Level 5,0.081570996978852,8.1570996978852,GPQA,0.305369127516779,7.38255033557047,MUSR,0.48071875,20.4231770833333,MMLU-PRO,0.399185505319149,33.2428339243499,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-03,2024-06-13,0,CohereForAI/c4ai-command-r-plus,cc-by-nc-4.0,1695,103.811,28.6315317116708 CohereForAI/c4ai-command-r-plus-08-2024_float16_2d8cf3ab0af78b9e43546486b096f86adf3ba4d0_True,CohereForAI/c4ai-command-r-plus-08-2024,2d8cf3ab0af78b9e43546486b096f86adf3ba4d0,float16,chatmodels,Original,CohereForCausalLM,33.5845340114894,TRUE,IFEval,0.753953953288386,75.3953953288386,BBH,0.599599991302719,42.836865407707,MATH Level 5,0.120090634441088,12.0090634441088,GPQA,0.350671140939597,13.4228187919463,MUSR,0.482947916666667,19.83515625,MMLU-PRO,0.442071143617021,38.0079048463357,TRUE,FALSE,FALSE,FALSE,TRUE,2024-08-21,2024-09-19,0,CohereForAI/c4ai-command-r-plus-08-2024,cc-by-nc-4.0,199,103.811,22.3188766676731 CohereForAI/c4ai-command-r-v01_float16_16881ccde1c68bbc7041280e6a66637bc46bfe88_True,CohereForAI/c4ai-command-r-v01,16881ccde1c68bbc7041280e6a66637bc46bfe88,float16,chatmodels,Original,CohereForCausalLM,25.3499784613365,TRUE,IFEval,0.674819478982433,67.4819478982433,BBH,0.540641551276786,34.5566592570583,MATH Level 5,0,0,GPQA,0.307046979865772,7.60626398210291,MUSR,0.451697916666667,16.12890625,MMLU-PRO,0.336934840425532,26.3260933806147,TRUE,FALSE,FALSE,FALSE,TRUE,2024-03-11,2024-06-13,0,CohereForAI/c4ai-command-r-v01,cc-by-nc-4.0,1068,34.981,13.3954372669898 Columbia-NLP/LION-Gemma-2b-dpo-v1.0_float16_a5f780075831374f8850324448acf94976dea504_True,Columbia-NLP/LION-Gemma-2b-dpo-v1.0,a5f780075831374f8850324448acf94976dea504,float16,chatmodels,Original,GemmaForCausalLM,11.4839947622434,TRUE,IFEval,0.327831265486686,32.7831265486686,BBH,0.391995636132075,14.5859760938158,MATH Level 5,0.0430513595166163,4.30513595166163,GPQA,0.249161073825503,0,MUSR,0.412010416666667,9.83463541666667,MMLU-PRO,0.16655585106383,7.39509456264775,FALSE,FALSE,FALSE,FALSE,FALSE,2024-06-28,2024-07-04,0,Columbia-NLP/LION-Gemma-2b-dpo-v1.0,"",0,2.506,0.97964847425047 @@ -227,7 +227,7 @@ DreadPoor/WIP_Damascus-8B-TIES_bfloat16_c7720a0b0a8d24e62bf71b0e955b1aca8e62f1cb DreadPoor/felix_dies-mistral-7B-model_stock_bfloat16_bb317aa7565625327e18c5158aebd4710aa1d925_False,DreadPoor/felix_dies-mistral-7B-model_stock,bb317aa7565625327e18c5158aebd4710aa1d925,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,18.1018281017421,FALSE,IFEval,0.300778600779266,30.0778600779266,BBH,0.490091807352742,28.8907980509645,MATH Level 5,0.0513595166163142,5.13595166163142,GPQA,0.291946308724832,5.59284116331097,MUSR,0.451822916666667,15.4778645833333,MMLU-PRO,0.310920877659575,23.4356530732861,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-09-30,0,Removed,"",0,7.242,0.661571667363575 DreadPoor/remember_to_breathe-8b-Model-Stock_bfloat16_fa88f1b06cf9ca7bd0d859c6a4b2240485363ae0_True,DreadPoor/remember_to_breathe-8b-Model-Stock,fa88f1b06cf9ca7bd0d859c6a4b2240485363ae0,bfloat16,basemergesandmoerges,Original,LlamaForCausalLM,28.1684073595337,TRUE,IFEval,0.710415032114789,71.0415032114789,BBH,0.541165443559992,34.6789907623163,MATH Level 5,0.143504531722054,14.3504531722054,GPQA,0.301174496644295,6.82326621923937,MUSR,0.414458333333333,11.440625,MMLU-PRO,0.37608045212766,30.6756057919622,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-12-06,0,Removed,"",0,8.03,0.663540162076869 EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2_bfloat16_2590214b30391392b9a84e7cbe40fff3a92c6814_True,EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2,2590214b30391392b9a84e7cbe40fff3a92c6814,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,43.5418377172999,TRUE,IFEval,0.687883704127271,68.7883704127271,BBH,0.708801222804876,59.0667326828602,MATH Level 5,0.390483383685801,39.0483383685801,GPQA,0.408557046979866,21.1409395973154,MUSR,0.471979166666667,19.7307291666667,MMLU-PRO,0.581283244680851,53.4759160756501,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-21,2024-11-27,1,Qwen/Qwen2.5-72B,other,9,72.706,22.95509846631 -EleutherAI/gpt-j-6b_bfloat16_47e169305d2e8376be1d31e765533382721b2cc1_False,EleutherAI/gpt-j-6b,47e169305d2e8376be1d31e765533382721b2cc1,bfloat16,pretrained,Original,GPTJForCausalLM,6.55782365211081,FALSE,IFEval,0.252218557870894,25.2218557870894,BBH,0.319104443103728,4.91281806832369,MATH Level 5,0.0128398791540786,1.28398791540786,GPQA,0.245805369127517,0,MUSR,0.36575,5.25208333333333,MMLU-PRO,0.124085771276596,2.67619680851064,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-08-19,0,EleutherAI/gpt-j-6b,apache-2.0,1453,6,0.767432156385538 +EleutherAI/gpt-j-6b_bfloat16_47e169305d2e8376be1d31e765533382721b2cc1_False,EleutherAI/gpt-j-6b,47e169305d2e8376be1d31e765533382721b2cc1,bfloat16,pretrained,Original,GPTJForCausalLM,6.55782365211081,FALSE,IFEval,0.252218557870894,25.2218557870894,BBH,0.319104443103728,4.91281806832369,MATH Level 5,0.0128398791540786,1.28398791540786,GPQA,0.245805369127517,0,MUSR,0.36575,5.25208333333333,MMLU-PRO,0.124085771276596,2.67619680851064,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-08-19,0,EleutherAI/gpt-j-6b,apache-2.0,1455,6,0.767432156385538 EleutherAI/gpt-neo-1.3B_bfloat16_dbe59a7f4a88d01d1ba9798d78dbe3fe038792c8_False,EleutherAI/gpt-neo-1.3B,dbe59a7f4a88d01d1ba9798d78dbe3fe038792c8,bfloat16,pretrained,Original,GPTNeoForCausalLM,5.34073838155464,FALSE,IFEval,0.207905025332784,20.7905025332784,BBH,0.303923158693564,3.02456918093099,MATH Level 5,0.00755287009063444,0.755287009063444,GPQA,0.255872483221477,0.782997762863532,MUSR,0.38165625,4.87369791666667,MMLU-PRO,0.116356382978723,1.81737588652482,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-12,0,EleutherAI/gpt-neo-1.3B,mit,269,1.366,0.359424061519048 EleutherAI/gpt-neo-125m_bfloat16_21def0189f5705e2521767faed922f1f15e7d7db_False,EleutherAI/gpt-neo-125m,21def0189f5705e2521767faed922f1f15e7d7db,bfloat16,pretrained,Original,GPTNeoForCausalLM,4.3821456739786,FALSE,IFEval,0.190544422133273,19.0544422133273,BBH,0.311515688579152,3.4367389514267,MATH Level 5,0.00453172205438066,0.453172205438066,GPQA,0.253355704697987,0.447427293064876,MUSR,0.359333333333333,2.61666666666667,MMLU-PRO,0.102559840425532,0.28442671394799,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-08-10,0,EleutherAI/gpt-neo-125m,mit,184,0.15,0.202902486593259 EleutherAI/gpt-neo-2.7B_bfloat16_e24fa291132763e59f4a5422741b424fb5d59056_False,EleutherAI/gpt-neo-2.7B,e24fa291132763e59f4a5422741b424fb5d59056,bfloat16,pretrained,Original,GPTNeoForCausalLM,6.3555191000811,FALSE,IFEval,0.258962885144749,25.8962885144749,BBH,0.313951603331525,4.17860266708101,MATH Level 5,0.00604229607250755,0.604229607250755,GPQA,0.265939597315436,2.12527964205817,MUSR,0.355364583333333,3.52057291666667,MMLU-PRO,0.116273271276596,1.80814125295508,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-12,0,EleutherAI/gpt-neo-2.7B,mit,446,2.718,0.508381401623291 @@ -244,7 +244,7 @@ Enno-Ai/EnnoAi-Pro-Llama-3.1-8B-v0.9_bfloat16_c740871122fd471a1a225cf2b4368e3337 EnnoAi/EnnoAi-Pro-Llama-3.1-8B-v1.0_bfloat16_c740871122fd471a1a225cf2b4368e333752d74c_True,EnnoAi/EnnoAi-Pro-Llama-3.1-8B-v1.0,c740871122fd471a1a225cf2b4368e333752d74c,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,14.9710896602936,TRUE,IFEval,0.470438436681339,47.0438436681339,BBH,0.416027208361901,17.4982963743828,MATH Level 5,0,0,GPQA,0.265939597315436,2.12527964205817,MUSR,0.383177083333333,5.43046875,MMLU-PRO,0.259557845744681,17.7286495271868,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-22,2024-09-06,0,EnnoAi/EnnoAi-Pro-Llama-3.1-8B-v1.0,apache-2.0,0,8.03,0.94564159228199 Epiculous/Azure_Dusk-v0.2_bfloat16_ebddf1b2efbe7f9cae066d263b0991ded89c88e8_True,Epiculous/Azure_Dusk-v0.2,ebddf1b2efbe7f9cae066d263b0991ded89c88e8,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,14.0508272195609,TRUE,IFEval,0.346715603487635,34.6715603487635,BBH,0.41197218735536,17.3964143923793,MATH Level 5,0.0181268882175227,1.81268882175227,GPQA,0.260906040268456,1.45413870246085,MUSR,0.383458333333333,6.365625,MMLU-PRO,0.303440824468085,22.6045360520095,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-09,2024-09-14,0,Epiculous/Azure_Dusk-v0.2,apache-2.0,7,12.248,1.99141139139846 Epiculous/Crimson_Dawn-v0.2_bfloat16_4cceb1e25026afef241ad5325097e88eccd8f37a_True,Epiculous/Crimson_Dawn-v0.2,4cceb1e25026afef241ad5325097e88eccd8f37a,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,14.8845408807215,TRUE,IFEval,0.310345438990767,31.0345438990767,BBH,0.448237964896454,21.6882485139553,MATH Level 5,0.0309667673716012,3.09667673716012,GPQA,0.276006711409396,3.4675615212528,MUSR,0.415177083333333,10.8971354166667,MMLU-PRO,0.272107712765957,19.1230791962175,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-02,2024-09-05,0,Epiculous/Crimson_Dawn-v0.2,apache-2.0,10,12.248,3.49238397097534 -Epiculous/NovaSpark_bfloat16_a46340895859e470c3e69661f0b894677cf4c5cb_True,Epiculous/NovaSpark,a46340895859e470c3e69661f0b894677cf4c5cb,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,25.2285617567326,TRUE,IFEval,0.640847396020337,64.0847396020337,BBH,0.50639586637683,29.526910688444,MATH Level 5,0.150302114803625,15.0302114803625,GPQA,0.297818791946309,6.3758389261745,MUSR,0.388197916666667,6.92473958333333,MMLU-PRO,0.364860372340426,29.4289302600473,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-13,2024-10-20,1,Epiculous/NovaSpark (Merge),apache-2.0,6,8.03,0.818185024708442 +Epiculous/NovaSpark_bfloat16_a46340895859e470c3e69661f0b894677cf4c5cb_True,Epiculous/NovaSpark,a46340895859e470c3e69661f0b894677cf4c5cb,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,25.2285617567326,TRUE,IFEval,0.640847396020337,64.0847396020337,BBH,0.50639586637683,29.526910688444,MATH Level 5,0.150302114803625,15.0302114803625,GPQA,0.297818791946309,6.3758389261745,MUSR,0.388197916666667,6.92473958333333,MMLU-PRO,0.364860372340426,29.4289302600473,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-13,2024-10-20,1,Epiculous/NovaSpark (Merge),apache-2.0,7,8.03,0.818185024708442 Epiculous/Violet_Twilight-v0.2_bfloat16_30c8bad3c1f565150afbf2fc90cacf4f45d096f6_True,Epiculous/Violet_Twilight-v0.2,30c8bad3c1f565150afbf2fc90cacf4f45d096f6,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,18.5527734874264,TRUE,IFEval,0.45317756885065,45.317756885065,BBH,0.461455247684589,23.9405372559019,MATH Level 5,0.0287009063444109,2.87009063444109,GPQA,0.265939597315436,2.12527964205817,MUSR,0.4299375,13.6088541666667,MMLU-PRO,0.31108710106383,23.4541223404255,TRUE,TRUE,FALSE,FALSE,FALSE,2024-09-12,2024-09-16,0,Epiculous/Violet_Twilight-v0.2,apache-2.0,18,12.248,1.77043599040323 EpistemeAI/Alpaca-Llama3.1-8B_float16_3152dfa17322dff7c6af6dbf3daceaf5db51e230_False,EpistemeAI/Alpaca-Llama3.1-8B,3152dfa17322dff7c6af6dbf3daceaf5db51e230,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,13.9221057683322,FALSE,IFEval,0.159869147196106,15.9869147196106,BBH,0.475526085397429,25.9352265551177,MATH Level 5,0.0468277945619335,4.68277945619335,GPQA,0.290268456375839,5.36912751677852,MUSR,0.340260416666667,6.59921875,MMLU-PRO,0.324634308510638,24.9593676122931,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-11,2024-08-13,2,meta-llama/Meta-Llama-3.1-8B,apache-2.0,0,8,0.920852587327145 EpistemeAI/Athena-gemma-2-2b-it_float16_661c1dc6a1a096222e33416e099bd02b7b970405_False,EpistemeAI/Athena-gemma-2-2b-it,661c1dc6a1a096222e33416e099bd02b7b970405,float16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,14.2943293927658,FALSE,IFEval,0.313417288350466,31.3417288350466,BBH,0.42642293591146,19.4178176744615,MATH Level 5,0.033987915407855,3.3987915407855,GPQA,0.268456375838926,2.46085011185682,MUSR,0.435052083333333,13.3481770833333,MMLU-PRO,0.2421875,15.7986111111111,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-29,2024-09-06,4,google/gemma-2-9b,apache-2.0,2,2,2.03679842688871 @@ -260,8 +260,8 @@ EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-0.001-128K-auto_float16_19b23c434 EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K_float16_b4a88fb5fb27fc5d8a503303cdb7aaeff373fd92_False,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K,b4a88fb5fb27fc5d8a503303cdb7aaeff373fd92,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,20.6271679065217,FALSE,IFEval,0.44573398582428,44.573398582428,BBH,0.489731992168606,28.0251607818872,MATH Level 5,0.120845921450151,12.0845921450151,GPQA,0.294463087248322,5.92841163310962,MUSR,0.376229166666667,4.8953125,MMLU-PRO,0.354305186170213,28.2561317966903,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-26,2024-10-05,1,Removed,apache-2.0,3,8,0.814786466083794 EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code_float16_8e8f1569a8a01ed3d6588f2669c730d4993355b5_False,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code,8e8f1569a8a01ed3d6588f2669c730d4993355b5,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,23.8969496076651,FALSE,IFEval,0.597533433511971,59.7533433511971,BBH,0.490419112262701,28.1718877821728,MATH Level 5,0.131419939577039,13.1419939577039,GPQA,0.302013422818792,6.93512304250559,MUSR,0.40103125,8.46223958333333,MMLU-PRO,0.342253989361702,26.917109929078,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-04,2024-10-05,2,Removed,apache-2.0,2,8,0.854317780904719 EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds_float16_8b73dd02349f0544c48c581cc73ada5cac6ff946_True,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds,8b73dd02349f0544c48c581cc73ada5cac6ff946,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,22.9931080609778,TRUE,IFEval,0.669099101495144,66.9099101495144,BBH,0.466807014316494,24.4626541689961,MATH Level 5,0.124622356495468,12.4622356495468,GPQA,0.272651006711409,3.02013422818792,MUSR,0.34178125,4.55598958333333,MMLU-PRO,0.338929521276596,26.5477245862884,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-14,2024-10-15,4,Removed,llama3.1,2,8,1.71673394455038 -EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto_float16_f18598c62a783bcc0d436a35df0c8a335e8ee5d7_True,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto,f18598c62a783bcc0d436a35df0c8a335e8ee5d7,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,23.7499407011867,TRUE,IFEval,0.730498410883123,73.0498410883124,BBH,0.464924667136924,24.5867370803527,MATH Level 5,0.139728096676737,13.9728096676737,GPQA,0.265939597315436,2.12527964205817,MUSR,0.320885416666667,1.21067708333333,MMLU-PRO,0.347988696808511,27.5542996453901,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-10-29,0,Removed,"",0,8.03,2.28530568307137 -EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto_bfloat16_055e87600d18e58594a8d193f45c0ee9a90e1780_True,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto,055e87600d18e58594a8d193f45c0ee9a90e1780,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,23.4888177899109,TRUE,IFEval,0.720706614006392,72.0706614006392,BBH,0.461009291550166,23.5442534065801,MATH Level 5,0.123111782477341,12.3111782477341,GPQA,0.27013422818792,2.68456375838927,MUSR,0.343239583333333,4.17161458333333,MMLU-PRO,0.335355718085106,26.1506353427896,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-11-27,0,Removed,"",0,8.03,0.672067770663859 +EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto_float16_f18598c62a783bcc0d436a35df0c8a335e8ee5d7_True,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto,f18598c62a783bcc0d436a35df0c8a335e8ee5d7,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,23.7499407011867,TRUE,IFEval,0.730498410883123,73.0498410883124,BBH,0.464924667136924,24.5867370803527,MATH Level 5,0.139728096676737,13.9728096676737,GPQA,0.265939597315436,2.12527964205817,MUSR,0.320885416666667,1.21067708333333,MMLU-PRO,0.347988696808511,27.5542996453901,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-21,2024-10-29,1,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto (Merge),apache-2.0,6,8.03,2.28530568307137 +EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto_bfloat16_055e87600d18e58594a8d193f45c0ee9a90e1780_True,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto,055e87600d18e58594a8d193f45c0ee9a90e1780,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,23.4888177899109,TRUE,IFEval,0.720706614006392,72.0706614006392,BBH,0.461009291550166,23.5442534065801,MATH Level 5,0.123111782477341,12.3111782477341,GPQA,0.27013422818792,2.68456375838927,MUSR,0.343239583333333,4.17161458333333,MMLU-PRO,0.335355718085106,26.1506353427896,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-21,2024-11-27,1,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto (Merge),apache-2.0,6,8.03,0.672067770663859 EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.004-128K-code-COT_float16_bb90c19dc7c4a509e7bd73f4620dca818b58be25_False,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.004-128K-code-COT,bb90c19dc7c4a509e7bd73f4620dca818b58be25,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,20.8322511715405,FALSE,IFEval,0.457824128866962,45.7824128866962,BBH,0.476052007960894,25.8208653758657,MATH Level 5,0.136706948640483,13.6706948640483,GPQA,0.293624161073826,5.8165548098434,MUSR,0.388135416666667,6.45026041666667,MMLU-PRO,0.347074468085106,27.4527186761229,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-11,2024-10-11,3,Removed,apache-2.0,0,8,0.839036565534646 EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.004-128K-code-ds-auto_bfloat16_db5ddb161ed26bc16baa814e31892dbe2f22b7a0_True,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.004-128K-code-ds-auto,db5ddb161ed26bc16baa814e31892dbe2f22b7a0,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,23.7609654890129,TRUE,IFEval,0.720481655341161,72.0481655341162,BBH,0.481779552581104,26.4520596044709,MATH Level 5,0.136706948640483,13.6706948640483,GPQA,0.248322147651007,0,MUSR,0.33,2.08333333333333,MMLU-PRO,0.354803856382979,28.3115395981088,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-14,2024-11-14,1,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.004-128K-code-ds-auto (Merge),apache-2.0,0,8,0.74513095477434 EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Math_bfloat16_677c97b4f92bfc330d4fae628e9a1df1ef606dcc_False,EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Math,677c97b4f92bfc330d4fae628e9a1df1ef606dcc,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,20.5453408732129,FALSE,IFEval,0.462295597902454,46.2295597902454,BBH,0.498295043207931,28.9593440938797,MATH Level 5,0.107250755287009,10.7250755287009,GPQA,0.291107382550336,5.48098434004475,MUSR,0.364072916666667,5.97578125,MMLU-PRO,0.33311170212766,25.9013002364066,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-23,2024-09-23,3,meta-llama/Meta-Llama-3.1-8B,apache-2.0,0,8.03,0.910271598090914 @@ -297,7 +297,7 @@ Etherll/Replete-LLM-V3-Llama-3.1-8b_float16_e79849d72f70ef74677ed81a8885403973b2 Etherll/SuperHermes_bfloat16_7edd56cb37722d09b0334826e0532b223d334939_False,Etherll/SuperHermes,7edd56cb37722d09b0334826e0532b223d334939,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,26.6046023223685,FALSE,IFEval,0.5459015412439,54.59015412439,BBH,0.528953179267985,32.8403167411728,MATH Level 5,0.146525679758308,14.6525679758308,GPQA,0.323825503355705,9.84340044742729,MUSR,0.440041666666667,14.9385416666667,MMLU-PRO,0.394863696808511,32.7626329787234,FALSE,FALSE,FALSE,FALSE,FALSE,2024-10-27,2024-10-27,1,Etherll/SuperHermes (Merge),"",1,8.03,0.750015414802549 Eurdem/Defne-llama3.1-8B_bfloat16_7832ba3066636bf4dab3e7d658c0b3ded12491ae_False,Eurdem/Defne-llama3.1-8B,7832ba3066636bf4dab3e7d658c0b3ded12491ae,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,25.0954291773948,FALSE,IFEval,0.503611528522099,50.3611528522099,BBH,0.532097909030824,32.8223813704349,MATH Level 5,0.158610271903323,15.8610271903323,GPQA,0.296140939597315,6.15212527964205,MUSR,0.43309375,13.53671875,MMLU-PRO,0.386552526595745,31.8391696217494,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-29,2024-08-14,0,Eurdem/Defne-llama3.1-8B,llama3.1,4,8.03,1.72030049359389 FallenMerick/Chewy-Lemon-Cookie-11B_bfloat16_0f5d0d6d218b3ef034f58eba32d6fe7ac4c237ae_False,FallenMerick/Chewy-Lemon-Cookie-11B,0f5d0d6d218b3ef034f58eba32d6fe7ac4c237ae,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,22.0185494201481,FALSE,IFEval,0.487524213531208,48.7524213531208,BBH,0.52511223073751,33.0143000884696,MATH Level 5,0.0528700906344411,5.28700906344411,GPQA,0.279362416107383,3.91498881431767,MUSR,0.454552083333333,15.95234375,MMLU-PRO,0.32671210106383,25.1902334515366,TRUE,TRUE,FALSE,FALSE,FALSE,2024-06-06,2024-06-27,1,FallenMerick/Chewy-Lemon-Cookie-11B (Merge),cc-by-4.0,0,10.732,0.85727377763601 -Felladrin/Llama-160M-Chat-v1_float16_e7f50665676821867ee7dfad32d0ca9fb68fc6bc_True,Felladrin/Llama-160M-Chat-v1,e7f50665676821867ee7dfad32d0ca9fb68fc6bc,float16,chatmodels,Original,LlamaForCausalLM,4.10106118080753,TRUE,IFEval,0.157546421273333,15.7546421273333,BBH,0.303608111463484,3.16675556939256,MATH Level 5,0,0,GPQA,0.25755033557047,1.00671140939597,MUSR,0.366125,3.165625,MMLU-PRO,0.113613696808511,1.5126329787234,TRUE,FALSE,FALSE,FALSE,FALSE,2023-12-20,2024-07-23,1,JackFram/llama-160m,apache-2.0,16,0.162,0.181580609139534 +Felladrin/Llama-160M-Chat-v1_float16_e7f50665676821867ee7dfad32d0ca9fb68fc6bc_True,Felladrin/Llama-160M-Chat-v1,e7f50665676821867ee7dfad32d0ca9fb68fc6bc,float16,chatmodels,Original,LlamaForCausalLM,4.10106118080753,TRUE,IFEval,0.157546421273333,15.7546421273333,BBH,0.303608111463484,3.16675556939256,MATH Level 5,0,0,GPQA,0.25755033557047,1.00671140939597,MUSR,0.366125,3.165625,MMLU-PRO,0.113613696808511,1.5126329787234,TRUE,FALSE,FALSE,FALSE,FALSE,2023-12-20,2024-07-23,1,JackFram/llama-160m,apache-2.0,17,0.162,0.181580609139534 Felladrin/Minueza-32M-UltraChat_float16_28506b99c5902d2215eb378ec91d4226a7396c49_True,Felladrin/Minueza-32M-UltraChat,28506b99c5902d2215eb378ec91d4226a7396c49,float16,chatmodels,Original,MistralForCausalLM,3.84872728727435,TRUE,IFEval,0.137562777873819,13.7562777873819,BBH,0.294147873404893,2.43728956228956,MATH Level 5,0,0,GPQA,0.255872483221477,0.782997762863532,MUSR,0.3741875,4.64010416666667,MMLU-PRO,0.11328125,1.47569444444444,TRUE,FALSE,FALSE,FALSE,FALSE,2024-02-27,2024-07-23,1,Felladrin/Minueza-32M-Base,apache-2.0,4,0.033,0.168066889517057 FlofloB/100k_fineweb_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit_float16_ea6ceae8a6894f1c6ea3fe978846b2a66c3e369c_True,FlofloB/100k_fineweb_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit,ea6ceae8a6894f1c6ea3fe978846b2a66c3e369c,float16,continuouslypretrained,Original,Qwen2ForCausalLM,7.87107214291845,TRUE,IFEval,0.308321919174457,30.8321919174457,BBH,0.332338744578946,7.34782500671502,MATH Level 5,0,0,GPQA,0.269295302013423,2.57270693512304,MUSR,0.33021875,0.944010416666666,MMLU-PRO,0.149767287234043,5.52969858156028,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-28,2024-11-29,3,Qwen/Qwen2.5-0.5B,apache-2.0,1,0.5,0.483693596223254 FlofloB/10k_continued_pretraining_Phi-3-mini-4k-instruct_Unsloth_merged_16bit_float16_a2eb0460779e76bb511339bcc2545b4729c9d78e_True,FlofloB/10k_continued_pretraining_Phi-3-mini-4k-instruct_Unsloth_merged_16bit,a2eb0460779e76bb511339bcc2545b4729c9d78e,float16,continuouslypretrained,Original,MistralForCausalLM,23.8799183752492,TRUE,IFEval,0.509730847484674,50.9730847484674,BBH,0.521498978412359,32.6077998308588,MATH Level 5,0.0876132930513595,8.76132930513595,GPQA,0.299496644295302,6.59955257270694,MUSR,0.430958333333333,13.5697916666667,MMLU-PRO,0.376911569148936,30.7679521276596,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-22,2024-11-22,1,unsloth/phi-3-mini-4k-instruct-bnb-4bit,apache-2.0,1,16,0.487544799875982 @@ -336,7 +336,7 @@ Gunulhona/Gemma-Ko-Merge_bfloat16_ca6b0eb1405f21db6a7a9cce3b112d21fcfdde97_True, Gunulhona/Gemma-Ko-Merge-PEFT_bfloat16_ca6b0eb1405f21db6a7a9cce3b112d21fcfdde97_False,Gunulhona/Gemma-Ko-Merge-PEFT,ca6b0eb1405f21db6a7a9cce3b112d21fcfdde97,bfloat16,fine-tunedondomain-specificdatasets,Adapter,?,18.1694945322647,FALSE,IFEval,0.28803906966848,28.803906966848,BBH,0.515409399978106,30.1862733313421,MATH Level 5,0,0,GPQA,0.324664429530201,9.95525727069351,MUSR,0.408010416666667,8.76796875,MMLU-PRO,0.38173204787234,31.3035608747045,FALSE,FALSE,FALSE,FALSE,FALSE,2024-09-30,2024-10-17,0,Gunulhona/Gemma-Ko-Merge-PEFT,"",0,20.318,5.87647672025824 Gunulhona/Gemma-Ko-Merge-PEFT_float16_ca6b0eb1405f21db6a7a9cce3b112d21fcfdde97_True,Gunulhona/Gemma-Ko-Merge-PEFT,ca6b0eb1405f21db6a7a9cce3b112d21fcfdde97,float16,chatmodels,Adapter,?,18.0662401703976,TRUE,IFEval,0.444134895410843,44.4134895410843,BBH,0.486298968782246,26.0150692958888,MATH Level 5,0,0,GPQA,0.307046979865772,7.60626398210291,MUSR,0.398583333333333,7.05625,MMLU-PRO,0.309757313829787,23.3063682033097,FALSE,FALSE,FALSE,FALSE,FALSE,2024-09-30,2024-10-23,0,Gunulhona/Gemma-Ko-Merge-PEFT,"",0,20.318,9.39433355207816 HPAI-BSC/Llama3-Aloe-8B-Alpha_bfloat16_f0bce5c1fee5ea2a6679bb3dc9de8548e7262c9e_True,HPAI-BSC/Llama3-Aloe-8B-Alpha,f0bce5c1fee5ea2a6679bb3dc9de8548e7262c9e,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,20.1045660887874,TRUE,IFEval,0.508107377314415,50.8107377314415,BBH,0.48308532966127,27.1459775775818,MATH Level 5,0.0536253776435045,5.36253776435045,GPQA,0.294463087248322,5.92841163310962,MUSR,0.367270833333333,5.87552083333334,MMLU-PRO,0.32953789893617,25.5042109929078,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-26,2024-10-29,0,HPAI-BSC/Llama3-Aloe-8B-Alpha,cc-by-nc-4.0,53,8.03,0.795244788688118 -HPAI-BSC/Llama3.1-Aloe-Beta-8B_bfloat16_3f2f0bbfb03cb0a8310efa50659688c1f2c02da0_True,HPAI-BSC/Llama3.1-Aloe-Beta-8B,3f2f0bbfb03cb0a8310efa50659688c1f2c02da0,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,23.7548094827747,TRUE,IFEval,0.725327686095117,72.5327686095117,BBH,0.509276076274886,30.3696247813448,MATH Level 5,0.0166163141993958,1.66163141993958,GPQA,0.268456375838926,2.46085011185682,MUSR,0.383458333333333,6.83229166666667,MMLU-PRO,0.358045212765957,28.6716903073286,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-30,2024-11-07,0,HPAI-BSC/Llama3.1-Aloe-Beta-8B,llama3.1,11,8.03,1.39869713266781 +HPAI-BSC/Llama3.1-Aloe-Beta-8B_bfloat16_3f2f0bbfb03cb0a8310efa50659688c1f2c02da0_True,HPAI-BSC/Llama3.1-Aloe-Beta-8B,3f2f0bbfb03cb0a8310efa50659688c1f2c02da0,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,23.7548094827747,TRUE,IFEval,0.725327686095117,72.5327686095117,BBH,0.509276076274886,30.3696247813448,MATH Level 5,0.0166163141993958,1.66163141993958,GPQA,0.268456375838926,2.46085011185682,MUSR,0.383458333333333,6.83229166666667,MMLU-PRO,0.358045212765957,28.6716903073286,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-30,2024-11-07,0,HPAI-BSC/Llama3.1-Aloe-Beta-8B,llama3.1,10,8.03,1.39869713266781 Hastagaras/Llama-3.1-Jamet-8B-MK.I_float16_26cb97042b04fee7d0140375a7babbf92278f8ac_True,Hastagaras/Llama-3.1-Jamet-8B-MK.I,26cb97042b04fee7d0140375a7babbf92278f8ac,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,25.3986297838594,TRUE,IFEval,0.733820706835641,73.3820706835641,BBH,0.504866643373316,29.5039047483195,MATH Level 5,0.125377643504532,12.5377643504532,GPQA,0.274328859060403,3.24384787472036,MUSR,0.372604166666667,6.1421875,MMLU-PRO,0.348238031914894,27.5820035460993,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-18,2024-11-18,0,Hastagaras/Llama-3.1-Jamet-8B-MK.I,llama3.1,1,8.03,0.718739898056177 Hastagaras/Zabuza-8B-Llama-3.1_bfloat16_57ffa92f229b8308916aae1d64d8f0dc9baa0a34_True,Hastagaras/Zabuza-8B-Llama-3.1,57ffa92f229b8308916aae1d64d8f0dc9baa0a34,bfloat16,basemergesandmoerges,Original,LlamaForCausalLM,19.7118289708866,TRUE,IFEval,0.626534262423703,62.6534262423703,BBH,0.45389157425462,23.2203208496705,MATH Level 5,0.0422960725075529,4.22960725075529,GPQA,0.264261744966443,1.90156599552573,MUSR,0.356791666666667,4.89895833333334,MMLU-PRO,0.292303856382979,21.3670951536643,TRUE,TRUE,FALSE,FALSE,FALSE,2024-11-05,2024-11-05,1,Hastagaras/Zabuza-8B-Llama-3.1 (Merge),llama3.1,0,8.03,0.675287308454302 HiroseKoichi/Llama-Salad-4x8B-V3_bfloat16_a343915429779efbd1478f01ba1f7fd9d8d226c0_True,HiroseKoichi/Llama-Salad-4x8B-V3,a343915429779efbd1478f01ba1f7fd9d8d226c0,bfloat16,basemergesandmoerges,Original,MixtralForCausalLM,24.9352898410171,TRUE,IFEval,0.665352376139754,66.5352376139754,BBH,0.524464978900175,31.9288488107451,MATH Level 5,0.0966767371601208,9.66767371601208,GPQA,0.302852348993289,7.04697986577182,MUSR,0.37403125,6.45390625,MMLU-PRO,0.351811835106383,27.9790927895981,TRUE,TRUE,TRUE,FALSE,FALSE,2024-06-17,2024-06-26,0,HiroseKoichi/Llama-Salad-4x8B-V3,llama3,5,24.942,2.13769520215148 @@ -351,7 +351,7 @@ HuggingFaceTB/SmolLM-135M-Instruct_bfloat16_8ca7af58e27777cae460ad8ca3ab9db15f5c HuggingFaceTB/SmolLM-360M_bfloat16_318cc630b73730bfd712e5873063156ffb8936b5_False,HuggingFaceTB/SmolLM-360M,318cc630b73730bfd712e5873063156ffb8936b5,bfloat16,pretrained,Original,LlamaForCausalLM,6.14759580602707,FALSE,IFEval,0.213350576470432,21.3350576470432,BBH,0.306451603331525,3.28491530324659,MATH Level 5,0.00453172205438067,0.453172205438067,GPQA,0.26761744966443,2.3489932885906,MUSR,0.40178125,8.08932291666667,MMLU-PRO,0.112367021276596,1.3741134751773,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-14,2024-07-18,0,HuggingFaceTB/SmolLM-360M,apache-2.0,62,0.36,0.365259532167126 HuggingFaceTB/SmolLM-360M-Instruct_bfloat16_8e951de8c220295ea4f85d078c4e320df7137535_True,HuggingFaceTB/SmolLM-360M-Instruct,8e951de8c220295ea4f85d078c4e320df7137535,bfloat16,chatmodels,Original,LlamaForCausalLM,4.70678415207999,TRUE,IFEval,0.195165494221998,19.5165494221998,BBH,0.288511143632177,2.08037429085374,MATH Level 5,0,0,GPQA,0.264261744966443,1.90156599552573,MUSR,0.347177083333333,2.89713541666667,MMLU-PRO,0.116605718085106,1.84507978723404,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-15,2024-08-20,1,HuggingFaceTB/SmolLM-360M,apache-2.0,77,0.362,0.366501024298985 HuggingFaceTB/SmolLM2-1.7B_bfloat16_4fa12cab4f5f53670b05125fb9d2873af587d231_False,HuggingFaceTB/SmolLM2-1.7B,4fa12cab4f5f53670b05125fb9d2873af587d231,bfloat16,pretrained,Original,LlamaForCausalLM,9.49550422402913,FALSE,IFEval,0.244000363480011,24.4000363480011,BBH,0.345259437716626,9.30178845955168,MATH Level 5,0.0211480362537764,2.11480362537764,GPQA,0.279362416107383,3.91498881431767,MUSR,0.348541666666667,4.60104166666667,MMLU-PRO,0.21376329787234,12.64036643026,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-30,2024-11-06,0,HuggingFaceTB/SmolLM2-1.7B,apache-2.0,85,1.71,0.325025991140308 -HuggingFaceTB/SmolLM2-1.7B-Instruct_bfloat16_d1bb90bcfbe0f211109880f4da18da66f229c4f6_True,HuggingFaceTB/SmolLM2-1.7B-Instruct,d1bb90bcfbe0f211109880f4da18da66f229c4f6,bfloat16,chatmodels,Original,LlamaForCausalLM,14.7453390971056,TRUE,IFEval,0.536783512192095,53.6783512192095,BBH,0.359861753141516,10.9179892262081,MATH Level 5,0.0415407854984894,4.15407854984894,GPQA,0.279362416107383,3.91498881431767,MUSR,0.342125,4.09895833333334,MMLU-PRO,0.205369015957447,11.7076684397163,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-31,2024-11-06,1,HuggingFaceTB/SmolLM2-1.7B-Instruct (Merge),apache-2.0,433,1.71,0.324960523121681 +HuggingFaceTB/SmolLM2-1.7B-Instruct_bfloat16_d1bb90bcfbe0f211109880f4da18da66f229c4f6_True,HuggingFaceTB/SmolLM2-1.7B-Instruct,d1bb90bcfbe0f211109880f4da18da66f229c4f6,bfloat16,chatmodels,Original,LlamaForCausalLM,14.7453390971056,TRUE,IFEval,0.536783512192095,53.6783512192095,BBH,0.359861753141516,10.9179892262081,MATH Level 5,0.0415407854984894,4.15407854984894,GPQA,0.279362416107383,3.91498881431767,MUSR,0.342125,4.09895833333334,MMLU-PRO,0.205369015957447,11.7076684397163,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-31,2024-11-06,1,HuggingFaceTB/SmolLM2-1.7B-Instruct (Merge),apache-2.0,432,1.71,0.324960523121681 HuggingFaceTB/SmolLM2-135M_bfloat16_28e66ca6931668447a3bac213f23d990ad3b0e2b_False,HuggingFaceTB/SmolLM2-135M,28e66ca6931668447a3bac213f23d990ad3b0e2b,bfloat16,pretrained,Original,LlamaForCausalLM,5.55767745404167,FALSE,IFEval,0.183300309844546,18.3300309844546,BBH,0.304423424687714,3.70807758683998,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.248322147651007,0,MUSR,0.411177083333333,10.03046875,MMLU-PRO,0.109458111702128,1.05090130023641,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-31,2024-11-06,0,HuggingFaceTB/SmolLM2-135M,apache-2.0,42,0.135,0.333904566630153 HuggingFaceTB/SmolLM2-135M-Instruct_bfloat16_5a33ba103645800d7b3790c4448546c1b73efc71_True,HuggingFaceTB/SmolLM2-135M-Instruct,5a33ba103645800d7b3790c4448546c1b73efc71,bfloat16,chatmodels,Original,LlamaForCausalLM,6.46736472035882,TRUE,IFEval,0.288313896018121,28.8313896018121,BBH,0.312432132806668,4.72080766080528,MATH Level 5,0.00302114803625378,0.302114803625378,GPQA,0.235738255033557,0,MUSR,0.36621875,3.67734375,MMLU-PRO,0.111452792553191,1.27253250591016,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-31,2024-11-06,1,HuggingFaceTB/SmolLM2-135M-Instruct (Merge),apache-2.0,73,0.135,0.338375628206877 HuggingFaceTB/SmolLM2-135M-Instruct_float16_5a33ba103645800d7b3790c4448546c1b73efc71_False,HuggingFaceTB/SmolLM2-135M-Instruct,5a33ba103645800d7b3790c4448546c1b73efc71,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,2.99259897065637,FALSE,IFEval,0.0592516744460254,5.92516744460254,BBH,0.313475029473359,4.79627574466244,MATH Level 5,0.00151057401812689,0.151057401812689,GPQA,0.234060402684564,0,MUSR,0.387145833333333,6.05989583333334,MMLU-PRO,0.109208776595745,1.02319739952719,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-31,2024-11-14,1,HuggingFaceTB/SmolLM2-135M-Instruct (Merge),apache-2.0,73,0.135,0.348753843693507 @@ -423,8 +423,8 @@ LEESM/llama-2-7b-hf-lora-oki10p_float16_d6e5af01616a038ac2b5cb83f458e490e1102244 LEESM/llama-3-8b-bnb-4b-kowiki231101_bfloat16_63b8f715daab6a0c7196a20855be8e85fe7ddcb4_False,LEESM/llama-3-8b-bnb-4b-kowiki231101,63b8f715daab6a0c7196a20855be8e85fe7ddcb4,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,9.27108845579953,FALSE,IFEval,0.168487391233039,16.8487391233039,BBH,0.413080565361718,16.9348681493017,MATH Level 5,0.00151057401812689,0.151057401812689,GPQA,0.270973154362416,2.79642058165548,MUSR,0.355145833333333,3.05989583333333,MMLU-PRO,0.242519946808511,15.8355496453901,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-08,2024-11-08,2,meta-llama/Meta-Llama-3.1-8B,apache-2.0,0,8.03,0.756887607200453 LEESM/llama-3-Korean-Bllossom-8B-trexlab-oki10p_float16_d105e0365510f9e5f8550558343083cab8523524_False,LEESM/llama-3-Korean-Bllossom-8B-trexlab-oki10p,d105e0365510f9e5f8550558343083cab8523524,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,12.9431976670495,FALSE,IFEval,0.213725138188894,21.3725138188894,BBH,0.434301211693207,19.7974357609114,MATH Level 5,0.0128398791540786,1.28398791540786,GPQA,0.275167785234899,3.35570469798658,MUSR,0.386927083333333,7.66588541666667,MMLU-PRO,0.317652925531915,24.183658392435,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-22,2024-11-08,0,LEESM/llama-3-Korean-Bllossom-8B-trexlab-oki10p,mit,0,8.03,0.758357790011608 LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct_bfloat16_7f15baedd46858153d817445aff032f4d6cf4939_True,LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct,7f15baedd46858153d817445aff032f4d6cf4939,bfloat16,chatmodels,Original,ExaoneForCausalLM,21.4034633257456,TRUE,IFEval,0.719282614573775,71.9282614573775,BBH,0.417443264778451,17.9773353951805,MATH Level 5,0.0445619335347432,4.45619335347432,GPQA,0.265939597315436,2.12527964205817,MUSR,0.366125,3.29895833333333,MMLU-PRO,0.357712765957447,28.6347517730497,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-31,2024-08-18,0,LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct,other,388,7.8,0.82512797747961 -LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct_float16_e949c91dec92095908d34e6b560af77dd0c993f8_True,LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct,e949c91dec92095908d34e6b560af77dd0c993f8,float16,chatmodels,Original,ExaoneForCausalLM,26.6907110058015,TRUE,IFEval,0.7950449252428,79.50449252428,BBH,0.409234711372341,15.9474371710569,MATH Level 5,0.340634441087613,34.0634441087613,GPQA,0.265939597315436,2.12527964205817,MUSR,0.366125,3.165625,MMLU-PRO,0.328041888297872,25.3379875886525,TRUE,FALSE,FALSE,FALSE,FALSE,2024-12-01,2024-12-11,0,LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct,other,72,2.4,0.60727146029865 -LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct_float16_0ff6b5ec7c13b049b253a16a889aa269e6b79a94_True,LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct,0ff6b5ec7c13b049b253a16a889aa269e6b79a94,float16,chatmodels,Original,ExaoneForCausalLM,31.4646519124242,TRUE,IFEval,0.813604569209697,81.3604569209697,BBH,0.472759230435986,25.653749420829,MATH Level 5,0.41012084592145,41.012084592145,GPQA,0.25755033557047,1.00671140939597,MUSR,0.3779375,4.9421875,MMLU-PRO,0.413314494680851,34.8127216312057,TRUE,FALSE,FALSE,FALSE,FALSE,2024-12-01,2024-12-11,0,LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct,other,69,7.8,0.719971670493439 +LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct_float16_e949c91dec92095908d34e6b560af77dd0c993f8_True,LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct,e949c91dec92095908d34e6b560af77dd0c993f8,float16,chatmodels,Original,ExaoneForCausalLM,26.6907110058015,TRUE,IFEval,0.7950449252428,79.50449252428,BBH,0.409234711372341,15.9474371710569,MATH Level 5,0.340634441087613,34.0634441087613,GPQA,0.265939597315436,2.12527964205817,MUSR,0.366125,3.165625,MMLU-PRO,0.328041888297872,25.3379875886525,TRUE,FALSE,FALSE,FALSE,FALSE,2024-12-01,2024-12-11,0,LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct,other,71,2.4,0.60727146029865 +LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct_float16_0ff6b5ec7c13b049b253a16a889aa269e6b79a94_True,LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct,0ff6b5ec7c13b049b253a16a889aa269e6b79a94,float16,chatmodels,Original,ExaoneForCausalLM,31.4646519124242,TRUE,IFEval,0.813604569209697,81.3604569209697,BBH,0.472759230435986,25.653749420829,MATH Level 5,0.41012084592145,41.012084592145,GPQA,0.25755033557047,1.00671140939597,MUSR,0.3779375,4.9421875,MMLU-PRO,0.413314494680851,34.8127216312057,TRUE,FALSE,FALSE,FALSE,FALSE,2024-12-01,2024-12-11,0,LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct,other,70,7.8,0.719971670493439 LLM360/K2_float16_49d159b6f2b64d562e745f0ff06e65b9a4c28ead_False,LLM360/K2,49d159b6f2b64d562e745f0ff06e65b9a4c28ead,float16,pretrained,Original,LlamaForCausalLM,14.5682245890329,FALSE,IFEval,0.225215760847884,22.5215760847884,BBH,0.497183567652368,28.2204028342011,MATH Level 5,0.0226586102719033,2.26586102719033,GPQA,0.276845637583893,3.57941834451902,MUSR,0.398,8.55,MMLU-PRO,0.300448803191489,22.2720892434988,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-17,2024-06-26,0,LLM360/K2,apache-2.0,80,65.286,8.83820641772923 LLM360/K2-Chat_bfloat16_5454f2d28031c9127e4227c873ca2f154e02e4c7_True,LLM360/K2-Chat,5454f2d28031c9127e4227c873ca2f154e02e4c7,bfloat16,chatmodels,Original,LlamaForCausalLM,22.9395117207926,TRUE,IFEval,0.515176398622322,51.5176398622322,BBH,0.535809963024207,33.793829235993,MATH Level 5,0.0166163141993958,1.66163141993958,GPQA,0.306208053691275,7.49440715883669,MUSR,0.457,16.825,MMLU-PRO,0.337101063829787,26.3445626477541,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-22,2024-06-12,0,LLM360/K2-Chat,apache-2.0,33,65.286,17.259828063151 LLM4Binary/llm4decompile-1.3b-v2_bfloat16_a347dabcb1ea9f21c9339bd764c150262e993b95_False,LLM4Binary/llm4decompile-1.3b-v2,a347dabcb1ea9f21c9339bd764c150262e993b95,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,6.85090804262261,FALSE,IFEval,0.226789363333732,22.6789363333732,BBH,0.327180841726759,5.91547543043847,MATH Level 5,0.00755287009063444,0.755287009063444,GPQA,0.235738255033557,0,MUSR,0.407177083333333,9.43046875,MMLU-PRO,0.120927526595745,2.32528073286052,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-18,2024-11-16,0,LLM4Binary/llm4decompile-1.3b-v2,mit,6,1.346,0.247582675941535 @@ -499,7 +499,7 @@ Lyte/Llama-3.2-1B-Instruct-COT-RL-Expriement1-EP04_bfloat16_59d93307c6f2cb7a29c5 Lyte/Llama-3.2-3B-Overthinker_float16_0e7af37fb3381365905fc2df24811c0e6d2ba5b2_True,Lyte/Llama-3.2-3B-Overthinker,0e7af37fb3381365905fc2df24811c0e6d2ba5b2,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,19.0778462402,TRUE,IFEval,0.640797528335926,64.0797528335926,BBH,0.432009309795252,20.0955822264572,MATH Level 5,0.0309667673716012,3.09667673716012,GPQA,0.259228187919463,1.23042505592841,MUSR,0.34190625,3.90494791666667,MMLU-PRO,0.298537234042553,22.0596926713948,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-17,2024-10-18,2,meta-llama/Llama-3.2-3B-Instruct,apache-2.0,18,3.213,0.733639697394509 M4-ai/TinyMistral-248M-v3_bfloat16_fa23fe617768c671f0bbbff1edf4556cfe844167_False,M4-ai/TinyMistral-248M-v3,fa23fe617768c671f0bbbff1edf4556cfe844167,bfloat16,pretrained,Original,MistralForCausalLM,4.13010760928209,FALSE,IFEval,0.163866319144315,16.3866319144315,BBH,0.288454993899557,1.77755393038632,MATH Level 5,0,0,GPQA,0.240771812080537,0,MUSR,0.379333333333333,5.15,MMLU-PRO,0.113198138297872,1.4664598108747,TRUE,FALSE,FALSE,FALSE,FALSE,2024-02-05,2024-10-18,0,M4-ai/TinyMistral-248M-v3,apache-2.0,4,0.248,0.234183611420779 MEscriva/ECE-PRYMMAL-0.5B-FT-V5-MUSR-Mathis_float16_7a9d848188a674302d64a865786d4508be19571a_False,MEscriva/ECE-PRYMMAL-0.5B-FT-V5-MUSR-Mathis,7a9d848188a674302d64a865786d4508be19571a,float16,fine-tunedondomain-specificdatasets,Adapter,?,3.81803368483764,FALSE,IFEval,0.0866290331874981,8.66290331874981,BBH,0.305728612437881,3.23777427104784,MATH Level 5,0.00453172205438067,0.453172205438067,GPQA,0.251677852348993,0.223713646532442,MUSR,0.40171875,8.61484375,MMLU-PRO,0.115442154255319,1.71579491725768,FALSE,FALSE,FALSE,FALSE,FALSE,2024-11-12,2024-11-19,0,MEscriva/ECE-PRYMMAL-0.5B-FT-V5-MUSR-Mathis,"",0,0.63,1.05155623119269 -MLP-KTLim/llama-3-Korean-Bllossom-8B_bfloat16_8a738f9f622ffc2b0a4a6b81dabbca80406248bf_True,MLP-KTLim/llama-3-Korean-Bllossom-8B,8a738f9f622ffc2b0a4a6b81dabbca80406248bf,bfloat16,chatmodels,Original,LlamaForCausalLM,20.333975762059,TRUE,IFEval,0.5112800702137,51.12800702137,BBH,0.490045564701877,26.9275279730551,MATH Level 5,0.0981873111782478,9.81873111782478,GPQA,0.26258389261745,1.67785234899329,MUSR,0.367458333333333,3.63229166666667,MMLU-PRO,0.359375,28.8194444444444,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-25,2024-07-09,1,MLP-KTLim/llama-3-Korean-Bllossom-8B (Merge),llama3,282,8.03,0.774720564334845 +MLP-KTLim/llama-3-Korean-Bllossom-8B_bfloat16_8a738f9f622ffc2b0a4a6b81dabbca80406248bf_True,MLP-KTLim/llama-3-Korean-Bllossom-8B,8a738f9f622ffc2b0a4a6b81dabbca80406248bf,bfloat16,chatmodels,Original,LlamaForCausalLM,20.333975762059,TRUE,IFEval,0.5112800702137,51.12800702137,BBH,0.490045564701877,26.9275279730551,MATH Level 5,0.0981873111782478,9.81873111782478,GPQA,0.26258389261745,1.67785234899329,MUSR,0.367458333333333,3.63229166666667,MMLU-PRO,0.359375,28.8194444444444,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-25,2024-07-09,1,MLP-KTLim/llama-3-Korean-Bllossom-8B (Merge),llama3,283,8.03,0.774720564334845 MTSAIR/Cotype-Nano_bfloat16_91817ff717dd16d216304fa9d749e08fce2aa38d_True,MTSAIR/Cotype-Nano,91817ff717dd16d216304fa9d749e08fce2aa38d,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,13.2588792361465,TRUE,IFEval,0.374792217981622,37.4792217981622,BBH,0.386494096960149,14.4468700232412,MATH Level 5,0.0641993957703928,6.41993957703928,GPQA,0.27013422818792,2.68456375838927,MUSR,0.328916666666667,2.11458333333333,MMLU-PRO,0.247672872340426,16.4080969267139,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-22,2024-12-01,0,MTSAIR/Cotype-Nano,other,43,1.544,0.49328801555598 MTSAIR/MultiVerse_70B_bfloat16_063430cdc4d972a0884e3e3e3d45ea4afbdf71a2_False,MTSAIR/MultiVerse_70B,063430cdc4d972a0884e3e3e3d45ea4afbdf71a2,bfloat16,chatmodels,Original,LlamaForCausalLM,32.0051903084749,FALSE,IFEval,0.524918327814643,52.4918327814643,BBH,0.618313428493118,46.135898982415,MATH Level 5,0.178247734138973,17.8247734138973,GPQA,0.354026845637584,13.8702460850112,MUSR,0.473989583333333,18.8153645833333,MMLU-PRO,0.486037234042553,42.8930260047281,TRUE,FALSE,FALSE,FALSE,FALSE,2024-03-25,2024-06-29,0,MTSAIR/MultiVerse_70B,other,39,72.289,13.6018173834864 Magpie-Align/Llama-3-8B-Magpie-Align-SFT-v0.1_bfloat16_1ed587f54f70334f495efb9c027acb03e96fe24f_True,Magpie-Align/Llama-3-8B-Magpie-Align-SFT-v0.1,1ed587f54f70334f495efb9c027acb03e96fe24f,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,15.9289113532727,TRUE,IFEval,0.436141659685191,43.6141659685191,BBH,0.461510274452737,23.9901243984113,MATH Level 5,0.0558912386706949,5.58912386706949,GPQA,0.26258389261745,1.67785234899329,MUSR,0.327739583333333,0,MMLU-PRO,0.286319813829787,20.702201536643,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-06,2024-09-17,1,meta-llama/Meta-Llama-3-8B,llama3,4,8.03,0.8335691386634 @@ -565,7 +565,7 @@ MaziyarPanahi/calme-3.1-instruct-78b_bfloat16_7ccd7f1a55ae79af7969f721bb7055511c MaziyarPanahi/calme-3.1-llamaloi-3b_bfloat16_62547548c06bb22f0b82c2bda7ac466507314a4b_True,MaziyarPanahi/calme-3.1-llamaloi-3b,62547548c06bb22f0b82c2bda7ac466507314a4b,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,24.0052338092847,TRUE,IFEval,0.73751756450662,73.751756450662,BBH,0.458734000499888,23.7691655758483,MATH Level 5,0.167673716012085,16.7673716012085,GPQA,0.281040268456376,4.13870246085012,MUSR,0.351520833333333,1.10677083333333,MMLU-PRO,0.320478723404255,24.4976359338062,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-07,2024-11-08,1,meta-llama/Llama-3.2-3B,llama3.2,1,3.213,1.19291766447292 MaziyarPanahi/calme-3.2-baguette-3b_bfloat16_bba8e602432bd467b64cabf9cb62326893060e60_True,MaziyarPanahi/calme-3.2-baguette-3b,bba8e602432bd467b64cabf9cb62326893060e60,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,22.1406481081638,TRUE,IFEval,0.633828242396841,63.3828242396841,BBH,0.470862269902714,25.8657466507311,MATH Level 5,0.0309667673716012,3.09667673716012,GPQA,0.294463087248322,5.92841163310962,MUSR,0.40209375,8.59505208333333,MMLU-PRO,0.333776595744681,25.9751773049645,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-07,2024-11-08,1,Qwen/Qwen2.5-3B,other,1,3.085,0.776012497501503 MaziyarPanahi/calme-3.2-instruct-3b_bfloat16_12347f5991157e752de6ba9f773a1bbc22445e3a_True,MaziyarPanahi/calme-3.2-instruct-3b,12347f5991157e752de6ba9f773a1bbc22445e3a,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,22.6566062728784,TRUE,IFEval,0.553319636342682,55.3319636342682,BBH,0.486564111037674,27.9767982423931,MATH Level 5,0.0989425981873112,9.89425981873112,GPQA,0.283557046979866,4.47427293064877,MUSR,0.404697916666667,8.78723958333333,MMLU-PRO,0.365275930851064,29.475103427896,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-07,2024-11-08,1,Qwen/Qwen2.5-3B,other,0,3.086,0.743433169169365 -MaziyarPanahi/calme-3.2-instruct-78b_bfloat16_731f4daf584f822f1393731ccff1d58c7f06b99e_True,MaziyarPanahi/calme-3.2-instruct-78b,731f4daf584f822f1393731ccff1d58c7f06b99e,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,52.0184433947031,TRUE,IFEval,0.806260721552148,80.6260721552148,BBH,0.731861627209267,62.6094432829016,MATH Level 5,0.399546827794562,39.9546827794562,GPQA,0.402684563758389,20.3579418344519,MUSR,0.602364583333333,38.52890625,MMLU-PRO,0.730302526595745,70.0336140661939,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-19,2024-11-28,1,Removed,other,22,77.965,33.0055653548694 +MaziyarPanahi/calme-3.2-instruct-78b_bfloat16_731f4daf584f822f1393731ccff1d58c7f06b99e_True,MaziyarPanahi/calme-3.2-instruct-78b,731f4daf584f822f1393731ccff1d58c7f06b99e,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,52.0184433947031,TRUE,IFEval,0.806260721552148,80.6260721552148,BBH,0.731861627209267,62.6094432829016,MATH Level 5,0.399546827794562,39.9546827794562,GPQA,0.402684563758389,20.3579418344519,MUSR,0.602364583333333,38.52890625,MMLU-PRO,0.730302526595745,70.0336140661939,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-19,2024-11-28,1,Removed,other,24,77.965,33.0055653548694 MaziyarPanahi/calme-3.3-baguette-3b_bfloat16_66f9438922503e5616b6b4488e96fd9342d5efb0_True,MaziyarPanahi/calme-3.3-baguette-3b,66f9438922503e5616b6b4488e96fd9342d5efb0,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,21.0626896485596,TRUE,IFEval,0.635951497581971,63.5951497581971,BBH,0.467821729595752,25.5965941060964,MATH Level 5,0,0,GPQA,0.280201342281879,4.0268456375839,MUSR,0.392822916666667,7.13619791666667,MMLU-PRO,0.334192154255319,26.0213504728132,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-07,2024-11-08,1,Qwen/Qwen2.5-3B,other,0,3.086,0.746922918806257 MaziyarPanahi/calme-3.3-instruct-3b_bfloat16_ea7d7fb442c981ecd44c5a9060ac6b062927f231_True,MaziyarPanahi/calme-3.3-instruct-3b,ea7d7fb442c981ecd44c5a9060ac6b062927f231,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,21.5477931531294,TRUE,IFEval,0.642321263137364,64.2321263137364,BBH,0.469334094276887,25.6821378185791,MATH Level 5,0,0,GPQA,0.282718120805369,4.36241610738255,MUSR,0.407427083333333,9.39505208333333,MMLU-PRO,0.330535239361702,25.6150265957447,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-07,2024-11-08,1,Qwen/Qwen2.5-3B,other,1,3.086,0.752548515201209 MultivexAI/Gladiator-Mini-Exp-1211-3B_float16_9f3f58da3fb4b1825c2b97effc421e7809c95848_True,MultivexAI/Gladiator-Mini-Exp-1211-3B,9f3f58da3fb4b1825c2b97effc421e7809c95848,float16,fine-tunedondomain-specificdatasets,Original,"",22.2218576631953,TRUE,IFEval,0.68760887777763,68.760887777763,BBH,0.448437526630281,22.1160624932153,MATH Level 5,0.134441087613293,13.4441087613293,GPQA,0.272651006711409,3.02013422818792,MUSR,0.326,2.08333333333333,MMLU-PRO,0.315159574468085,23.9066193853428,TRUE,FALSE,FALSE,FALSE,FALSE,2024-12-11,2024-12-11,1,MultivexAI/Gladiator-Mini-Exp-1211-3B (Merge),mit,0,3,0.595781409541183 @@ -584,7 +584,7 @@ NAPS-ai/naps-llama-3_1_instruct-v0.6.0_float16_e0ce03ea6539f9398adbe14d8f9512e54 NLPark/AnFeng_v3.1-Avocet_float16_5170739731033323e6e66a0f68d34790042a3b2a_False,NLPark/AnFeng_v3.1-Avocet,5170739731033323e6e66a0f68d34790042a3b2a,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,28.2776632974634,FALSE,IFEval,0.509631112115853,50.9631112115853,BBH,0.582852329074409,40.3090336514533,MATH Level 5,0.152567975830816,15.2567975830816,GPQA,0.324664429530201,9.95525727069351,MUSR,0.447572916666667,14.9799479166667,MMLU-PRO,0.443816489361702,38.2018321513002,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-03,2024-08-07,0,NLPark/AnFeng_v3.1-Avocet,cc-by-nc-nd-4.0,0,34.393,3.17200803334586 NLPark/B-and-W_Flycatcher-3AD1E_bfloat16_21044e39f6854f5a6df84c5074d449b7eb96b522_True,NLPark/B-and-W_Flycatcher-3AD1E,21044e39f6854f5a6df84c5074d449b7eb96b522,bfloat16,chatmodels,Original,LlamaForCausalLM,29.2840499717512,TRUE,IFEval,0.490846509483725,49.0846509483725,BBH,0.606511752853436,43.7424580109235,MATH Level 5,0.166918429003021,16.6918429003021,GPQA,0.330536912751678,10.738255033557,MUSR,0.442270833333333,13.8838541666667,MMLU-PRO,0.47406914893617,41.5632387706856,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-28,2024-09-28,0,NLPark/B-and-W_Flycatcher-3AD1E,apache-2.0,0,14.77,1.55132229692418 NLPark/Shi-Ci-Robin-Test_3AD80_bfloat16_995887837a259817570489183cbe8b1abffd23b1_True,NLPark/Shi-Ci-Robin-Test_3AD80,995887837a259817570489183cbe8b1abffd23b1,bfloat16,chatmodels,Original,LlamaForCausalLM,38.5165993626602,TRUE,IFEval,0.722654778210703,72.2654778210703,BBH,0.670480515757033,52.2656617511021,MATH Level 5,0.272658610271903,27.2658610271903,GPQA,0.35989932885906,14.6532438478747,MUSR,0.46959375,18.8658854166667,MMLU-PRO,0.512051196808511,45.7834663120567,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-25,2024-10-25,1,NLPark/Shi-Ci-Robin-Test_3AD80 (Merge),llama3.1,0,70.554,12.446754480357 -NTQAI/Nxcode-CQ-7B-orpo_bfloat16_74f3b3c06de36b261af9ef857279d6e33f893336_True,NTQAI/Nxcode-CQ-7B-orpo,74f3b3c06de36b261af9ef857279d6e33f893336,bfloat16,chatmodels,Original,Qwen2ForCausalLM,12.2982509985398,TRUE,IFEval,0.400721197533655,40.0721197533655,BBH,0.414302324917822,17.5800048700814,MATH Level 5,0.0173716012084592,1.73716012084592,GPQA,0.254194630872483,0.559284116331097,MUSR,0.39396875,7.04609375,MMLU-PRO,0.161153590425532,6.79484338061466,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-24,2024-08-10,0,NTQAI/Nxcode-CQ-7B-orpo,other,108,7.25,0.842174913393591 +NTQAI/Nxcode-CQ-7B-orpo_bfloat16_74f3b3c06de36b261af9ef857279d6e33f893336_True,NTQAI/Nxcode-CQ-7B-orpo,74f3b3c06de36b261af9ef857279d6e33f893336,bfloat16,chatmodels,Original,Qwen2ForCausalLM,12.2982509985398,TRUE,IFEval,0.400721197533655,40.0721197533655,BBH,0.414302324917822,17.5800048700814,MATH Level 5,0.0173716012084592,1.73716012084592,GPQA,0.254194630872483,0.559284116331097,MUSR,0.39396875,7.04609375,MMLU-PRO,0.161153590425532,6.79484338061466,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-24,2024-08-10,0,NTQAI/Nxcode-CQ-7B-orpo,other,109,7.25,0.842174913393591 NYTK/PULI-GPTrio_float16_16a56dd22d184e4b7b49d90461fa8d4810639463_False,NYTK/PULI-GPTrio,16a56dd22d184e4b7b49d90461fa8d4810639463,float16,pretrained,Original,GPTNeoXForCausalLM,5.77078732696787,FALSE,IFEval,0.217971648559156,21.7971648559156,BBH,0.306002909062375,3.0152211415705,MATH Level 5,0.00830815709969789,0.830815709969789,GPQA,0.265939597315436,2.12527964205817,MUSR,0.381875,5.334375,MMLU-PRO,0.113696808510638,1.52186761229314,TRUE,FALSE,FALSE,FALSE,FALSE,2023-06-08,2024-08-24,0,NYTK/PULI-GPTrio,cc-by-nc-4.0,10,7.673,0.722046995347682 NYTK/PULI-LlumiX-32K_float16_a589894397a36b61c578d0dd4778ee6e5fe471ff_False,NYTK/PULI-LlumiX-32K,a589894397a36b61c578d0dd4778ee6e5fe471ff,float16,continuouslypretrained,Original,LlamaForCausalLM,6.40581630535552,FALSE,IFEval,0.169961258350067,16.9961258350067,BBH,0.318935822429494,5.10704712990773,MATH Level 5,0.00604229607250755,0.604229607250755,GPQA,0.253355704697987,0.447427293064876,MUSR,0.396416666666667,7.71875,MMLU-PRO,0.168051861702128,7.56131796690307,TRUE,FALSE,FALSE,FALSE,FALSE,2024-03-12,2024-08-24,0,NYTK/PULI-LlumiX-32K,llama2,9,6.738,0.822569739962814 Naveenpoliasetty/llama3-8B-V2_float16_e0458381d02bc411b9e576796d185f23dcc11f71_False,Naveenpoliasetty/llama3-8B-V2,e0458381d02bc411b9e576796d185f23dcc11f71,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,20.8458629712676,FALSE,IFEval,0.412261687877055,41.2261687877055,BBH,0.518865758006506,30.8732094250396,MATH Level 5,0.0800604229607251,8.00604229607251,GPQA,0.290268456375839,5.36912751677852,MUSR,0.408135416666667,9.18359375,MMLU-PRO,0.373753324468085,30.4170360520095,FALSE,FALSE,FALSE,FALSE,FALSE,2024-06-18,2024-06-26,1,Naveenpoliasetty/llama3-8B-V2 (Merge),"",1,8.03,0.75201223968556 @@ -612,11 +612,11 @@ NotASI/FineTome-Llama3.2-1B-0929_float16_61c8742238d0cfe68a0a3f61326b84cd6624ad0 NotASI/FineTome-Llama3.2-3B-1002_float16_7c8497a24a381e3bfd77bc92e5685442768790d0_True,NotASI/FineTome-Llama3.2-3B-1002,7c8497a24a381e3bfd77bc92e5685442768790d0,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,16.6491072536234,TRUE,IFEval,0.547449655802161,54.7449655802161,BBH,0.431947061402534,19.5200606524888,MATH Level 5,0.0558912386706949,5.58912386706949,GPQA,0.250838926174497,0.111856823266221,MUSR,0.368510416666667,3.96380208333333,MMLU-PRO,0.243683510638298,15.9648345153664,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-04,2024-10-05,2,meta-llama/Llama-3.2-3B-Instruct,llama3.2,1,3,1.41970552115749 NotASI/FineTome-v1.5-Llama3.2-1B-1007_float16_5e329d987e9f74dd2703a4fefa56ab8c72b5702b_True,NotASI/FineTome-v1.5-Llama3.2-1B-1007,5e329d987e9f74dd2703a4fefa56ab8c72b5702b,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,8.94045538932633,TRUE,IFEval,0.392377779846363,39.2377779846363,BBH,0.324056711214857,5.80172467354176,MATH Level 5,0.013595166163142,1.3595166163142,GPQA,0.25,0,MUSR,0.347458333333333,2.49895833333333,MMLU-PRO,0.142702792553192,4.74475472813239,TRUE,TRUE,FALSE,FALSE,FALSE,2024-10-07,2024-10-07,1,NotASI/FineTome-v1.5-Llama3.2-1B-1007 (Merge),llama3.2,1,1.236,0.474231520771542 NotASI/FineTome-v1.5-Llama3.2-3B-1007_float16_6c6e71fbcff6c00d04a3fd69084af20bf2a943c8_True,NotASI/FineTome-v1.5-Llama3.2-3B-1007,6c6e71fbcff6c00d04a3fd69084af20bf2a943c8,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,16.9626388108139,TRUE,IFEval,0.550771951754678,55.0771951754678,BBH,0.431237293532158,19.4572192788493,MATH Level 5,0.0551359516616314,5.51359516616314,GPQA,0.261744966442953,1.56599552572707,MUSR,0.364541666666667,4.06770833333333,MMLU-PRO,0.244847074468085,16.0941193853428,TRUE,TRUE,FALSE,FALSE,FALSE,2024-10-07,2024-10-07,1,NotASI/FineTome-v1.5-Llama3.2-3B-1007 (Merge),llama3.2,1,3.213,0.725378525425475 -NousResearch/Hermes-2-Pro-Llama-3-8B_float16_bc265d1781299ed2045214289c927c207439a729_True,NousResearch/Hermes-2-Pro-Llama-3-8B,bc265d1781299ed2045214289c927c207439a729,float16,chatmodels,Original,LlamaForCausalLM,21.7049203338117,TRUE,IFEval,0.536183991808402,53.6183991808402,BBH,0.507112624310082,30.667993420825,MATH Level 5,0.0619335347432024,6.19335347432024,GPQA,0.292785234899329,5.70469798657718,MUSR,0.426239583333333,11.2466145833333,MMLU-PRO,0.305186170212766,22.798463356974,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-30,2024-06-13,1,NousResearch/Meta-Llama-3-8B,llama3,411,8.031,0.749983206264044 +NousResearch/Hermes-2-Pro-Llama-3-8B_float16_bc265d1781299ed2045214289c927c207439a729_True,NousResearch/Hermes-2-Pro-Llama-3-8B,bc265d1781299ed2045214289c927c207439a729,float16,chatmodels,Original,LlamaForCausalLM,21.7049203338117,TRUE,IFEval,0.536183991808402,53.6183991808402,BBH,0.507112624310082,30.667993420825,MATH Level 5,0.0619335347432024,6.19335347432024,GPQA,0.292785234899329,5.70469798657718,MUSR,0.426239583333333,11.2466145833333,MMLU-PRO,0.305186170212766,22.798463356974,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-30,2024-06-13,1,NousResearch/Meta-Llama-3-8B,llama3,412,8.031,0.749983206264044 NousResearch/Hermes-2-Pro-Mistral-7B_bfloat16_09317b1d8da639b5d9af77c06aa17cde0f0f91c0_True,NousResearch/Hermes-2-Pro-Mistral-7B,09317b1d8da639b5d9af77c06aa17cde0f0f91c0,bfloat16,chatmodels,Original,MistralForCausalLM,21.7021075222127,TRUE,IFEval,0.566833778817981,56.6833778817981,BBH,0.499543533049808,29.427578860536,MATH Level 5,0.0521148036253777,5.21148036253777,GPQA,0.273489932885906,3.13199105145414,MUSR,0.43759375,14.1325520833333,MMLU-PRO,0.294630984042553,21.625664893617,TRUE,FALSE,FALSE,FALSE,TRUE,2024-03-11,2024-06-12,1,mistralai/Mistral-7B-v0.1,apache-2.0,487,7.242,0.472797519360034 NousResearch/Hermes-2-Theta-Llama-3-8B_bfloat16_885173e97ab8572b444f7db1290d5d0386e26816_True,NousResearch/Hermes-2-Theta-Llama-3-8B,885173e97ab8572b444f7db1290d5d0386e26816,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,24.7757883439893,TRUE,IFEval,0.651788365980044,65.1788365980044,BBH,0.520667226091187,32.0460738480758,MATH Level 5,0.0959214501510574,9.59214501510574,GPQA,0.303691275167785,7.15883668903803,MUSR,0.394895833333333,8.36197916666667,MMLU-PRO,0.336851728723404,26.3168587470449,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-05,2024-07-11,2,NousResearch/Meta-Llama-3-8B,apache-2.0,195,8.03,0.743922417596867 NousResearch/Hermes-3-Llama-3.1-70B_bfloat16_093242c69a91f8d9d5b8094c380b88772f9bd7f8_True,NousResearch/Hermes-3-Llama-3.1-70B,093242c69a91f8d9d5b8094c380b88772f9bd7f8,bfloat16,chatmodels,Original,LlamaForCausalLM,37.4825450944456,TRUE,IFEval,0.76614383169989,76.614383169989,BBH,0.675578064138748,53.7654086913006,MATH Level 5,0.148036253776435,14.8036253776435,GPQA,0.361577181208054,14.8769574944072,MUSR,0.494895833333333,23.4286458333333,MMLU-PRO,0.47265625,41.40625,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-29,2024-08-28,1,meta-llama/Meta-Llama-3.1-70B,llama3,98,70.554,11.2078909209213 -NousResearch/Hermes-3-Llama-3.1-8B_bfloat16_aabb745a717e133b74dcae23195d2635cf5f38cc_True,NousResearch/Hermes-3-Llama-3.1-8B,aabb745a717e133b74dcae23195d2635cf5f38cc,bfloat16,chatmodels,Original,LlamaForCausalLM,23.49087671148,TRUE,IFEval,0.617017291896612,61.7017291896612,BBH,0.517745254014125,30.724096614148,MATH Level 5,0.047583081570997,4.7583081570997,GPQA,0.297818791946309,6.3758389261745,MUSR,0.4369375,13.6171875,MMLU-PRO,0.31391289893617,23.7680998817967,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-28,2024-08-28,1,meta-llama/Meta-Llama-3.1-8B,llama3,258,8.03,0.905807900142943 +NousResearch/Hermes-3-Llama-3.1-8B_bfloat16_aabb745a717e133b74dcae23195d2635cf5f38cc_True,NousResearch/Hermes-3-Llama-3.1-8B,aabb745a717e133b74dcae23195d2635cf5f38cc,bfloat16,chatmodels,Original,LlamaForCausalLM,23.49087671148,TRUE,IFEval,0.617017291896612,61.7017291896612,BBH,0.517745254014125,30.724096614148,MATH Level 5,0.047583081570997,4.7583081570997,GPQA,0.297818791946309,6.3758389261745,MUSR,0.4369375,13.6171875,MMLU-PRO,0.31391289893617,23.7680998817967,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-28,2024-08-28,1,meta-llama/Meta-Llama-3.1-8B,llama3,259,8.03,0.905807900142943 NousResearch/Nous-Hermes-2-Mistral-7B-DPO_bfloat16_ebec0a691037d38955727d6949798429a63929dd_True,NousResearch/Nous-Hermes-2-Mistral-7B-DPO,ebec0a691037d38955727d6949798429a63929dd,bfloat16,chatmodels,Original,MistralForCausalLM,21.0376463902847,TRUE,IFEval,0.57625101397625,57.625101397625,BBH,0.485265366546524,27.7925456583661,MATH Level 5,0.0438066465256798,4.38066465256798,GPQA,0.292785234899329,5.70469798657718,MUSR,0.399979166666667,8.33072916666667,MMLU-PRO,0.301529255319149,22.3921394799054,TRUE,FALSE,FALSE,FALSE,TRUE,2024-02-18,2024-06-12,1,mistralai/Mistral-7B-v0.1,apache-2.0,169,7.242,0.474598918698818 NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO_bfloat16_286ae6737d048ad1d965c2e830864df02db50f2f_True,NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO,286ae6737d048ad1d965c2e830864df02db50f2f,bfloat16,chatmodels,Original,MixtralForCausalLM,27.290249854483,TRUE,IFEval,0.58968980083955,58.968980083955,BBH,0.553885138403382,37.1077837913399,MATH Level 5,0.118580060422961,11.8580060422961,GPQA,0.321308724832215,9.50782997762864,MUSR,0.459541666666667,16.6760416666667,MMLU-PRO,0.366605718085106,29.6228575650118,TRUE,FALSE,TRUE,FALSE,TRUE,2024-01-11,2024-07-27,1,mistralai/Mixtral-8x7B-v0.1,apache-2.0,420,46.703,12.8651437241499 NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT_bfloat16_4c06af2684730f75a6874b95e8bf6058105d9612_True,NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT,4c06af2684730f75a6874b95e8bf6058105d9612,bfloat16,chatmodels,Original,MixtralForCausalLM,21.8410108914617,TRUE,IFEval,0.573078321076965,57.3078321076965,BBH,0.505786845402664,30.5943127788644,MATH Level 5,0.0211480362537764,2.11480362537764,GPQA,0.302013422818792,6.93512304250559,MUSR,0.421375,11.1385416666667,MMLU-PRO,0.306599069148936,22.9554521276596,TRUE,FALSE,TRUE,FALSE,TRUE,2023-12-26,2024-06-12,1,mistralai/Mixtral-8x7B-v0.1,apache-2.0,55,46.703,10.3879398461721 @@ -688,7 +688,7 @@ PrimeIntellect/INTELLECT-1_float16_3b8d48b5ce11ee9526495f1db9eb1644518bfce0_Fals PrimeIntellect/INTELLECT-1-Instruct_bfloat16_a672cbe91f9bd4df58f90619ca3c2acb2eb11294_True,PrimeIntellect/INTELLECT-1-Instruct,a672cbe91f9bd4df58f90619ca3c2acb2eb11294,bfloat16,chatmodels,Original,LlamaForCausalLM,1.0282675380783,TRUE,IFEval,0,0,BBH,0.286980078012147,1.74944787031375,MATH Level 5,0,0,GPQA,0.248322147651007,0,MUSR,0.3576875,3.7109375,MMLU-PRO,0.106382978723404,0.709219858156028,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-28,2024-11-29,1,PrimeIntellect/INTELLECT-1-Instruct (Merge),apache-2.0,111,10.211,1.88997871140833 PygmalionAI/pygmalion-6b_float16_2a0d74449c8fbf0378194e95f64aa92e16297294_False,PygmalionAI/pygmalion-6b,2a0d74449c8fbf0378194e95f64aa92e16297294,float16,fine-tunedondomain-specificdatasets,Original,GPTJForCausalLM,5.3923596589092,FALSE,IFEval,0.20910406610017,20.910406610017,BBH,0.3198894464386,5.08957714398891,MATH Level 5,0.00604229607250755,0.604229607250755,GPQA,0.249161073825503,0,MUSR,0.368354166666667,3.7109375,MMLU-PRO,0.118351063829787,2.03900709219858,TRUE,FALSE,FALSE,FALSE,TRUE,2023-01-07,2024-06-12,0,PygmalionAI/pygmalion-6b,creativeml-openrail-m,735,6,31.9231192804799 Q-bert/MetaMath-1B_float16_da62756f069aba78d07d4c76108e246cb91dbc35_True,Q-bert/MetaMath-1B,da62756f069aba78d07d4c76108e246cb91dbc35,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,11.3242479106733,TRUE,IFEval,0.530039184918239,53.0039184918239,BBH,0.345068636779295,8.43461064483256,MATH Level 5,0,0,GPQA,0.251677852348993,0.223713646532442,MUSR,0.328916666666667,0.78125,MMLU-PRO,0.14951795212766,5.50199468085107,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-09-30,0,Removed,"",0,1.236,0.465027993931676 -Qwen/QwQ-32B-Preview_bfloat16_1032e81cb936c486aae1d33da75b2fbcd5deed4a_True,Qwen/QwQ-32B-Preview,1032e81cb936c486aae1d33da75b2fbcd5deed4a,bfloat16,chatmodels,Original,Qwen2ForCausalLM,30.444123257489,TRUE,IFEval,0.403543708471301,40.3543708471301,BBH,0.669138148225274,53.3876763517132,MATH Level 5,0.228851963746224,22.8851963746224,GPQA,0.281879194630873,4.25055928411634,MUSR,0.410989583333333,9.80703125,MMLU-PRO,0.56781914893617,51.9799054373523,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-27,2024-11-29,2,Qwen/Qwen2.5-32B,apache-2.0,1256,32.764,10.2103897762396 +Qwen/QwQ-32B-Preview_bfloat16_1032e81cb936c486aae1d33da75b2fbcd5deed4a_True,Qwen/QwQ-32B-Preview,1032e81cb936c486aae1d33da75b2fbcd5deed4a,bfloat16,chatmodels,Original,Qwen2ForCausalLM,30.444123257489,TRUE,IFEval,0.403543708471301,40.3543708471301,BBH,0.669138148225274,53.3876763517132,MATH Level 5,0.228851963746224,22.8851963746224,GPQA,0.281879194630873,4.25055928411634,MUSR,0.410989583333333,9.80703125,MMLU-PRO,0.56781914893617,51.9799054373523,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-27,2024-11-29,2,Qwen/Qwen2.5-32B,apache-2.0,1271,32.764,10.2103897762396 Qwen/Qwen1.5-0.5B_bfloat16_8f445e3628f3500ee69f24e1303c9f10f5342a39_False,Qwen/Qwen1.5-0.5B,8f445e3628f3500ee69f24e1303c9f10f5342a39,bfloat16,pretrained,Original,Qwen2ForCausalLM,5.13701708767239,FALSE,IFEval,0.17056077873376,17.056077873376,BBH,0.315353865914256,5.03547583679937,MATH Level 5,0.00453172205438067,0.453172205438067,GPQA,0.254194630872483,0.559284116331097,MUSR,0.361625,4.303125,MMLU-PRO,0.130734707446809,3.41496749408983,TRUE,FALSE,FALSE,FALSE,TRUE,2024-01-22,2024-06-13,0,Qwen/Qwen1.5-0.5B,other,145,0.62,0.978737373550742 Qwen/Qwen1.5-0.5B-Chat_bfloat16_4d14e384a4b037942bb3f3016665157c8bcb70ea_True,Qwen/Qwen1.5-0.5B-Chat,4d14e384a4b037942bb3f3016665157c8bcb70ea,bfloat16,chatmodels,Original,Qwen2ForCausalLM,5.56486903979377,TRUE,IFEval,0.180727137328954,18.0727137328954,BBH,0.316666215203671,4.31803263693806,MATH Level 5,0,0,GPQA,0.269295302013423,2.57270693512304,MUSR,0.383708333333333,6.06354166666667,MMLU-PRO,0.121259973404255,2.36221926713948,TRUE,FALSE,FALSE,FALSE,TRUE,2024-01-31,2024-06-12,0,Qwen/Qwen1.5-0.5B-Chat,other,75,0.62,0.54974439031725 Qwen/Qwen1.5-1.8B_bfloat16_7846de7ed421727b318d6605a0bfab659da2c067_False,Qwen/Qwen1.5-1.8B,7846de7ed421727b318d6605a0bfab659da2c067,bfloat16,pretrained,Original,Qwen2ForCausalLM,9.18137570437486,FALSE,IFEval,0.215423963971152,21.5423963971152,BBH,0.347612155836631,9.75990158772794,MATH Level 5,0.0264350453172205,2.64350453172205,GPQA,0.305369127516779,7.38255033557047,MUSR,0.360510416666667,3.96380208333333,MMLU-PRO,0.188164893617021,9.79609929078014,TRUE,FALSE,FALSE,FALSE,TRUE,2024-01-22,2024-06-13,0,Qwen/Qwen1.5-1.8B,other,43,1.837,0.948870786599621 @@ -714,33 +714,33 @@ Qwen/Qwen2-57B-A14B-Instruct_bfloat16_5ea455a449e61a92a5b194ee06be807647d3e8b5_T Qwen/Qwen2-72B_bfloat16_87993795c78576318087f70b43fbf530eb7789e7_False,Qwen/Qwen2-72B,87993795c78576318087f70b43fbf530eb7789e7,bfloat16,pretrained,Original,Qwen2ForCausalLM,35.4818471661096,FALSE,IFEval,0.382361024304401,38.2361024304401,BBH,0.661734029856643,51.8561311869552,MATH Level 5,0.312688821752266,31.2688821752266,GPQA,0.394295302013423,19.2393736017897,MUSR,0.470364583333333,19.72890625,MMLU-PRO,0.573055186170213,52.5616873522459,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-22,2024-06-26,0,Qwen/Qwen2-72B,other,192,72.706,64.0622792398665 Qwen/Qwen2-72B-Instruct_bfloat16_1af63c698f59c4235668ec9c1395468cb7cd7e79_False,Qwen/Qwen2-72B-Instruct,1af63c698f59c4235668ec9c1395468cb7cd7e79,bfloat16,chatmodels,Original,Qwen2ForCausalLM,42.9143041555209,FALSE,IFEval,0.7989168738946,79.89168738946,BBH,0.697730968386067,57.483009118763,MATH Level 5,0.376888217522659,37.6888217522659,GPQA,0.37248322147651,16.331096196868,MUSR,0.456010416666667,17.16796875,MMLU-PRO,0.540309175531915,48.9232417257683,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-28,2024-06-26,1,Qwen/Qwen2-72B,other,684,72.706,37.5539744227 Qwen/Qwen2-7B_bfloat16_453ed1575b739b5b03ce3758b23befdb0967f40e_False,Qwen/Qwen2-7B,453ed1575b739b5b03ce3758b23befdb0967f40e,bfloat16,pretrained,Original,Qwen2ForCausalLM,23.9377502573001,FALSE,IFEval,0.31486677571067,31.486677571067,BBH,0.531531595001889,34.7111362027534,MATH Level 5,0.204682779456193,20.4682779456193,GPQA,0.304530201342282,7.27069351230425,MUSR,0.443916666666667,14.3229166666667,MMLU-PRO,0.418301196808511,35.3667996453901,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-04,2024-06-09,0,Qwen/Qwen2-7B,apache-2.0,144,7.616,1.28058225557584 -Qwen/Qwen2-7B-Instruct_bfloat16_41c66b0be1c3081f13defc6bdf946c2ef240d6a6_True,Qwen/Qwen2-7B-Instruct,41c66b0be1c3081f13defc6bdf946c2ef240d6a6,bfloat16,chatmodels,Original,Qwen2ForCausalLM,24.9029516291134,TRUE,IFEval,0.567907596288958,56.7907596288958,BBH,0.554478156379319,37.8083909231017,MATH Level 5,0.0944108761329305,9.44108761329305,GPQA,0.297818791946309,6.3758389261745,MUSR,0.392791666666667,7.365625,MMLU-PRO,0.384724069148936,31.6360076832151,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-04,2024-06-12,1,Qwen/Qwen2-7B,apache-2.0,600,7.616,1.04203898585749 +Qwen/Qwen2-7B-Instruct_bfloat16_41c66b0be1c3081f13defc6bdf946c2ef240d6a6_True,Qwen/Qwen2-7B-Instruct,41c66b0be1c3081f13defc6bdf946c2ef240d6a6,bfloat16,chatmodels,Original,Qwen2ForCausalLM,24.9029516291134,TRUE,IFEval,0.567907596288958,56.7907596288958,BBH,0.554478156379319,37.8083909231017,MATH Level 5,0.0944108761329305,9.44108761329305,GPQA,0.297818791946309,6.3758389261745,MUSR,0.392791666666667,7.365625,MMLU-PRO,0.384724069148936,31.6360076832151,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-04,2024-06-12,1,Qwen/Qwen2-7B,apache-2.0,601,7.616,1.04203898585749 Qwen/Qwen2-Math-72B-Instruct_bfloat16_5c267882f3377bcfc35882f8609098a894eeeaa8_True,Qwen/Qwen2-Math-72B-Instruct,5c267882f3377bcfc35882f8609098a894eeeaa8,bfloat16,chatmodels,Original,Qwen2ForCausalLM,35.1508663678517,TRUE,IFEval,0.569381463405985,56.9381463405985,BBH,0.634337660025181,47.9601995073491,MATH Level 5,0.381419939577039,38.1419939577039,GPQA,0.368288590604027,15.7718120805369,MUSR,0.451697916666667,15.72890625,MMLU-PRO,0.427277260638298,36.364140070922,TRUE,FALSE,FALSE,FALSE,TRUE,2024-08-08,2024-08-19,0,Qwen/Qwen2-Math-72B-Instruct,other,87,72.706,12.1682476948271 Qwen/Qwen2-Math-7B_bfloat16_47a44ff4136da8960adbab02b2326787086bcf6c_True,Qwen/Qwen2-Math-7B,47a44ff4136da8960adbab02b2326787086bcf6c,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,11.9413924471103,TRUE,IFEval,0.26870481433707,26.870481433707,BBH,0.386954741074792,14.0644944888713,MATH Level 5,0.243202416918429,24.3202416918429,GPQA,0.263422818791946,1.78970917225951,MUSR,0.359333333333333,2.41666666666667,MMLU-PRO,0.11968085106383,2.18676122931442,TRUE,FALSE,FALSE,FALSE,TRUE,2024-08-08,2024-08-19,0,Qwen/Qwen2-Math-7B,apache-2.0,13,7.616,1.5630360629051 Qwen/Qwen2-VL-72B-Instruct_bfloat16_f400120e59a6196b024298b7d09fb517f742db7d_True,Qwen/Qwen2-VL-72B-Instruct,f400120e59a6196b024298b7d09fb517f742db7d,bfloat16,multimodal,Original,Qwen2VLForConditionalGeneration,37.9127528860119,TRUE,IFEval,0.598232689264485,59.8232689264485,BBH,0.694628729233868,56.3112338791251,MATH Level 5,0.246978851963746,24.6978851963746,GPQA,0.38758389261745,18.34451901566,MUSR,0.44921875,15.8856770833333,MMLU-PRO,0.57172539893617,52.41393321513,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-10-20,1,Qwen/Qwen2-VL-72B-Instruct (Merge),other,213,73.406,27.2497165156002 -Qwen/Qwen2-VL-7B-Instruct_bfloat16_51c47430f97dd7c74aa1fa6825e68a813478097f_True,Qwen/Qwen2-VL-7B-Instruct,51c47430f97dd7c74aa1fa6825e68a813478097f,bfloat16,multimodal,Original,Qwen2VLForConditionalGeneration,24.2148096194201,TRUE,IFEval,0.459921896124505,45.9921896124505,BBH,0.546450715906999,35.8771031449895,MATH Level 5,0.0619335347432024,6.19335347432024,GPQA,0.319630872483222,9.2841163310962,MUSR,0.4375,13.5541666666667,MMLU-PRO,0.409491356382979,34.3879284869976,TRUE,FALSE,FALSE,FALSE,TRUE,2024-08-28,2024-10-20,1,Qwen/Qwen2-VL-7B-Instruct (Merge),apache-2.0,922,8.291,1.05438228472396 +Qwen/Qwen2-VL-7B-Instruct_bfloat16_51c47430f97dd7c74aa1fa6825e68a813478097f_True,Qwen/Qwen2-VL-7B-Instruct,51c47430f97dd7c74aa1fa6825e68a813478097f,bfloat16,multimodal,Original,Qwen2VLForConditionalGeneration,24.2148096194201,TRUE,IFEval,0.459921896124505,45.9921896124505,BBH,0.546450715906999,35.8771031449895,MATH Level 5,0.0619335347432024,6.19335347432024,GPQA,0.319630872483222,9.2841163310962,MUSR,0.4375,13.5541666666667,MMLU-PRO,0.409491356382979,34.3879284869976,TRUE,FALSE,FALSE,FALSE,TRUE,2024-08-28,2024-10-20,1,Qwen/Qwen2-VL-7B-Instruct (Merge),apache-2.0,927,8.291,1.05438228472396 Qwen/Qwen2.5-0.5B_bfloat16_2630d3d2321bc1f1878f702166d1b2af019a7310_False,Qwen/Qwen2.5-0.5B,2630d3d2321bc1f1878f702166d1b2af019a7310,bfloat16,pretrained,Original,Qwen2ForCausalLM,6.31089339476025,FALSE,IFEval,0.162717146061339,16.271714606134,BBH,0.327481481511966,6.95396163488226,MATH Level 5,0.0249244712990937,2.49244712990937,GPQA,0.246644295302013,0,MUSR,0.343333333333333,2.08333333333333,MMLU-PRO,0.190575132978723,10.0639036643026,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-15,2024-09-19,0,Qwen/Qwen2.5-0.5B,apache-2.0,134,0.5,1.16534262881835 -Qwen/Qwen2.5-0.5B-Instruct_bfloat16_a8b602d9dafd3a75d382e62757d83d89fca3be54_True,Qwen/Qwen2.5-0.5B-Instruct,a8b602d9dafd3a75d382e62757d83d89fca3be54,bfloat16,chatmodels,Original,Qwen2ForCausalLM,8.14064731927608,TRUE,IFEval,0.307122878407071,30.7122878407071,BBH,0.334072921493727,8.43486361058883,MATH Level 5,0,0,GPQA,0.25755033557047,1.00671140939597,MUSR,0.332885416666667,0.944010416666666,MMLU-PRO,0.169714095744681,7.74601063829787,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-09-19,1,Qwen/Qwen2.5-0.5B,apache-2.0,138,0.5,0.63082445281977 -Qwen/Qwen2.5-0.5B-Instruct_float16_7ae557604adf67be50417f59c2c2f167def9a775_True,Qwen/Qwen2.5-0.5B-Instruct,7ae557604adf67be50417f59c2c2f167def9a775,float16,chatmodels,Original,Qwen2ForCausalLM,8.38297184669106,TRUE,IFEval,0.315291205113543,31.5291205113543,BBH,0.332191642954914,8.16950226818277,MATH Level 5,0,0,GPQA,0.259228187919463,1.23042505592841,MUSR,0.3341875,1.3734375,MMLU-PRO,0.171958111702128,7.99534574468085,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-10-16,1,Qwen/Qwen2.5-0.5B,apache-2.0,138,0.494,0.618575974583338 +Qwen/Qwen2.5-0.5B-Instruct_bfloat16_a8b602d9dafd3a75d382e62757d83d89fca3be54_True,Qwen/Qwen2.5-0.5B-Instruct,a8b602d9dafd3a75d382e62757d83d89fca3be54,bfloat16,chatmodels,Original,Qwen2ForCausalLM,8.14064731927608,TRUE,IFEval,0.307122878407071,30.7122878407071,BBH,0.334072921493727,8.43486361058883,MATH Level 5,0,0,GPQA,0.25755033557047,1.00671140939597,MUSR,0.332885416666667,0.944010416666666,MMLU-PRO,0.169714095744681,7.74601063829787,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-09-19,1,Qwen/Qwen2.5-0.5B,apache-2.0,139,0.5,0.63082445281977 +Qwen/Qwen2.5-0.5B-Instruct_float16_7ae557604adf67be50417f59c2c2f167def9a775_True,Qwen/Qwen2.5-0.5B-Instruct,7ae557604adf67be50417f59c2c2f167def9a775,float16,chatmodels,Original,Qwen2ForCausalLM,8.38297184669106,TRUE,IFEval,0.315291205113543,31.5291205113543,BBH,0.332191642954914,8.16950226818277,MATH Level 5,0,0,GPQA,0.259228187919463,1.23042505592841,MUSR,0.3341875,1.3734375,MMLU-PRO,0.171958111702128,7.99534574468085,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-10-16,1,Qwen/Qwen2.5-0.5B,apache-2.0,139,0.494,0.618575974583338 Qwen/Qwen2.5-1.5B_bfloat16_e5dfabbcffd9b0c7b31d89b82c5a6b72e663f32c_False,Qwen/Qwen2.5-1.5B,e5dfabbcffd9b0c7b31d89b82c5a6b72e663f32c,bfloat16,pretrained,Original,Qwen2ForCausalLM,13.8023486940494,FALSE,IFEval,0.267430417957686,26.7430417957686,BBH,0.407795094513661,16.6604651676919,MATH Level 5,0.088368580060423,8.8368580060423,GPQA,0.285234899328859,4.6979865771812,MUSR,0.35759375,5.26588541666667,MMLU-PRO,0.285488696808511,20.6098552009456,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-15,2024-09-19,0,Qwen/Qwen2.5-1.5B,apache-2.0,47,1.5,1.24850101000351 -Qwen/Qwen2.5-1.5B-Instruct_bfloat16_5fee7c4ed634dc66c6e318c8ac2897b8b9154536_True,Qwen/Qwen2.5-1.5B-Instruct,5fee7c4ed634dc66c6e318c8ac2897b8b9154536,bfloat16,chatmodels,Original,Qwen2ForCausalLM,15.0317176008589,TRUE,IFEval,0.447556926732182,44.7556926732182,BBH,0.428898274042291,19.809786497359,MATH Level 5,0.0166163141993958,1.66163141993958,GPQA,0.255872483221477,0.782997762863532,MUSR,0.3663125,3.1890625,MMLU-PRO,0.279920212765957,19.9911347517731,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-09-19,1,Qwen/Qwen2.5-1.5B,apache-2.0,239,1.5,0.687189331195425 +Qwen/Qwen2.5-1.5B-Instruct_bfloat16_5fee7c4ed634dc66c6e318c8ac2897b8b9154536_True,Qwen/Qwen2.5-1.5B-Instruct,5fee7c4ed634dc66c6e318c8ac2897b8b9154536,bfloat16,chatmodels,Original,Qwen2ForCausalLM,15.0317176008589,TRUE,IFEval,0.447556926732182,44.7556926732182,BBH,0.428898274042291,19.809786497359,MATH Level 5,0.0166163141993958,1.66163141993958,GPQA,0.255872483221477,0.782997762863532,MUSR,0.3663125,3.1890625,MMLU-PRO,0.279920212765957,19.9911347517731,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-09-19,1,Qwen/Qwen2.5-1.5B,apache-2.0,241,1.5,0.687189331195425 Qwen/Qwen2.5-14B_bfloat16_83a1904df002b00bc8db6f877821cb77dbb363b0_False,Qwen/Qwen2.5-14B,83a1904df002b00bc8db6f877821cb77dbb363b0,bfloat16,pretrained,Original,Qwen2ForCausalLM,31.7496528240654,FALSE,IFEval,0.369446402212795,36.9446402212795,BBH,0.616051493531774,45.0783124049849,MATH Level 5,0.277945619335347,27.7945619335347,GPQA,0.381711409395973,17.5615212527964,MUSR,0.450239583333333,15.91328125,MMLU-PRO,0.52485039893617,47.2055998817967,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-15,2024-09-19,0,Qwen/Qwen2.5-14B,apache-2.0,44,14.77,5.58592135172473 Qwen/Qwen2.5-14B-Instruct_bfloat16_f55224c616ca27d4bcf28969a156de12c98981cf_True,Qwen/Qwen2.5-14B-Instruct,f55224c616ca27d4bcf28969a156de12c98981cf,bfloat16,chatmodels,Original,Qwen2ForCausalLM,32.1830727842617,TRUE,IFEval,0.815777692079239,81.5777692079239,BBH,0.639045370590622,48.3607066128271,MATH Level 5,0,0,GPQA,0.322147651006711,9.61968680089485,MUSR,0.4100625,10.1578125,MMLU-PRO,0.490442154255319,43.3824615839244,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-09-18,1,Qwen/Qwen2.5-14B,apache-2.0,137,14.77,1.7736503203376 Qwen/Qwen2.5-32B_bfloat16_ff23665d01c3665be5fdb271d18a62090b65c06d_False,Qwen/Qwen2.5-32B,ff23665d01c3665be5fdb271d18a62090b65c06d,bfloat16,pretrained,Original,Qwen2ForCausalLM,37.9827910715109,FALSE,IFEval,0.407664995545154,40.7664995545154,BBH,0.677052244872651,53.954752851332,MATH Level 5,0.354984894259819,35.4984894259819,GPQA,0.411912751677852,21.5883668903803,MUSR,0.497833333333333,22.6958333333333,MMLU-PRO,0.580535239361702,53.3928043735225,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-15,2024-09-19,0,Qwen/Qwen2.5-32B,apache-2.0,51,32.764,5.87488554274725 -Qwen/Qwen2.5-32B-Instruct_bfloat16_70e8dfb9ad18a7d499f765fe206ff065ed8ca197_True,Qwen/Qwen2.5-32B-Instruct,70e8dfb9ad18a7d499f765fe206ff065ed8ca197,bfloat16,chatmodels,Original,Qwen2ForCausalLM,36.174184974139,TRUE,IFEval,0.834612162395777,83.4612162395777,BBH,0.691252508013434,56.4893482615939,MATH Level 5,0,0,GPQA,0.338087248322148,11.744966442953,MUSR,0.426125,13.4989583333333,MMLU-PRO,0.566655585106383,51.8506205673759,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-09-19,1,Qwen/Qwen2.5-32B,apache-2.0,148,32.764,5.75248317034287 +Qwen/Qwen2.5-32B-Instruct_bfloat16_70e8dfb9ad18a7d499f765fe206ff065ed8ca197_True,Qwen/Qwen2.5-32B-Instruct,70e8dfb9ad18a7d499f765fe206ff065ed8ca197,bfloat16,chatmodels,Original,Qwen2ForCausalLM,36.174184974139,TRUE,IFEval,0.834612162395777,83.4612162395777,BBH,0.691252508013434,56.4893482615939,MATH Level 5,0,0,GPQA,0.338087248322148,11.744966442953,MUSR,0.426125,13.4989583333333,MMLU-PRO,0.566655585106383,51.8506205673759,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-09-19,1,Qwen/Qwen2.5-32B,apache-2.0,149,32.764,5.75248317034287 Qwen/Qwen2.5-3B_bfloat16_e4aa5ac50aa507415cda96cc99eb77ad0a3d2d34_False,Qwen/Qwen2.5-3B,e4aa5ac50aa507415cda96cc99eb77ad0a3d2d34,bfloat16,pretrained,Original,Qwen2ForCausalLM,17.1083089890835,FALSE,IFEval,0.268954152759124,26.8954152759124,BBH,0.461247534101163,24.3042417263717,MATH Level 5,0.088368580060423,8.8368580060423,GPQA,0.297818791946309,6.3758389261745,MUSR,0.430333333333333,11.7583333333333,MMLU-PRO,0.3203125,24.4791666666667,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-15,2024-09-27,0,Qwen/Qwen2.5-3B,other,41,3.086,3.81050747400589 Qwen/Qwen2.5-3B-Instruct_bfloat16_82f42baa094a9600e39ccd80d34058aeeb3abbc1_True,Qwen/Qwen2.5-3B-Instruct,82f42baa094a9600e39ccd80d34058aeeb3abbc1,bfloat16,chatmodels,Original,Qwen2ForCausalLM,21.0313443188007,TRUE,IFEval,0.647491987925371,64.7491987925372,BBH,0.469276665604885,25.8013939440886,MATH Level 5,0,0,GPQA,0.272651006711409,3.02013422818792,MUSR,0.396791666666667,7.565625,MMLU-PRO,0.325465425531915,25.0517139479905,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-09-19,1,Qwen/Qwen2.5-3B,other,114,3,1.38847430558096 Qwen/Qwen2.5-72B_bfloat16_587cc4061cf6a7cc0d429d05c109447e5cf063af_False,Qwen/Qwen2.5-72B,587cc4061cf6a7cc0d429d05c109447e5cf063af,bfloat16,pretrained,Original,Qwen2ForCausalLM,38.3656148716295,FALSE,IFEval,0.413710067066495,41.3710067066495,BBH,0.679732067069485,54.6150578016369,MATH Level 5,0.386706948640483,38.6706948640483,GPQA,0.405201342281879,20.6935123042506,MUSR,0.477125,19.640625,MMLU-PRO,0.596825132978723,55.2027925531915,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-15,2024-09-19,0,Qwen/Qwen2.5-72B,other,44,72.706,18.0919265899938 -Qwen/Qwen2.5-72B-Instruct_bfloat16_a13fff9ad76700c7ecff2769f75943ba8395b4a7_True,Qwen/Qwen2.5-72B-Instruct,a13fff9ad76700c7ecff2769f75943ba8395b4a7,bfloat16,chatmodels,Original,Qwen2ForCausalLM,38.2120812616148,TRUE,IFEval,0.863837949972739,86.3837949972739,BBH,0.727274732174482,61.8732556687879,MATH Level 5,0.0120845921450151,1.20845921450151,GPQA,0.375,16.6666666666667,MUSR,0.420604166666667,11.7421875,MMLU-PRO,0.562583111702128,51.3981235224587,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-10-16,1,Qwen/Qwen2.5-72B,other,591,72.706,33.0067683243991 +Qwen/Qwen2.5-72B-Instruct_bfloat16_a13fff9ad76700c7ecff2769f75943ba8395b4a7_True,Qwen/Qwen2.5-72B-Instruct,a13fff9ad76700c7ecff2769f75943ba8395b4a7,bfloat16,chatmodels,Original,Qwen2ForCausalLM,38.2120812616148,TRUE,IFEval,0.863837949972739,86.3837949972739,BBH,0.727274732174482,61.8732556687879,MATH Level 5,0.0120845921450151,1.20845921450151,GPQA,0.375,16.6666666666667,MUSR,0.420604166666667,11.7421875,MMLU-PRO,0.562583111702128,51.3981235224587,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-10-16,1,Qwen/Qwen2.5-72B,other,594,72.706,33.0067683243991 Qwen/Qwen2.5-7B_bfloat16_57597c00770845ceba45271ba1b24c94bbcc7baf_False,Qwen/Qwen2.5-7B,57597c00770845ceba45271ba1b24c94bbcc7baf,bfloat16,pretrained,Original,Qwen2ForCausalLM,24.9869343450417,FALSE,IFEval,0.337447971382598,33.7447971382598,BBH,0.541630376778862,35.8134732875478,MATH Level 5,0.188821752265861,18.8821752265861,GPQA,0.324664429530201,9.95525727069351,MUSR,0.442427083333333,14.13671875,MMLU-PRO,0.436502659574468,37.3891843971631,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-15,2024-09-19,0,Qwen/Qwen2.5-7B,apache-2.0,80,7.616,3.02796087914288 Qwen/Qwen2.5-7B-Instruct_bfloat16_52e20a6f5f475e5c8f6a8ebda4ae5fa6b1ea22ac_True,Qwen/Qwen2.5-7B-Instruct,52e20a6f5f475e5c8f6a8ebda4ae5fa6b1ea22ac,bfloat16,chatmodels,Original,Qwen2ForCausalLM,26.8667753266146,TRUE,IFEval,0.7585251576927,75.85251576927,BBH,0.53942319682991,34.8921167587655,MATH Level 5,0,0,GPQA,0.291107382550336,5.48098434004475,MUSR,0.40203125,8.45390625,MMLU-PRO,0.428690159574468,36.5211288416076,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-09-18,1,Qwen/Qwen2.5-7B,apache-2.0,354,7.616,2.16827148311528 Qwen/Qwen2.5-Coder-14B_bfloat16_1db30eb5ec86a6e51d8981818ee2910370b3010d_True,Qwen/Qwen2.5-Coder-14B,1db30eb5ec86a6e51d8981818ee2910370b3010d,bfloat16,pretrained,Original,Qwen2ForCausalLM,24.7661116962997,TRUE,IFEval,0.347265256186917,34.7265256186917,BBH,0.586486009174123,40.523002115363,MATH Level 5,0.221299093655589,22.1299093655589,GPQA,0.292785234899329,5.70469798657718,MUSR,0.387364583333333,6.38723958333334,MMLU-PRO,0.452127659574468,39.1252955082742,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-08,2024-11-12,1,Qwen/Qwen2.5-Coder-14B (Merge),apache-2.0,22,14.77,3.63262520075326 Qwen/Qwen2.5-Coder-14B-Instruct_bfloat16_1a62978099f9b19f72fdd191988ff958abb18561_True,Qwen/Qwen2.5-Coder-14B-Instruct,1a62978099f9b19f72fdd191988ff958abb18561,bfloat16,chatmodels,Original,Qwen2ForCausalLM,31.1787254167968,TRUE,IFEval,0.690756082749327,69.0756082749327,BBH,0.614029642366133,44.2200182156684,MATH Level 5,0.268126888217523,26.8126888217523,GPQA,0.304530201342282,7.27069351230425,MUSR,0.391458333333333,7.03229166666667,MMLU-PRO,0.393949468085106,32.6610520094563,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-06,2024-11-12,1,Qwen/Qwen2.5-Coder-14B-Instruct (Merge),apache-2.0,58,14.77,1.38321406525897 -Qwen/Qwen2.5-Coder-32B_float16_2e12b5f7bc878d424d222e224ed40aee564ec45f_False,Qwen/Qwen2.5-Coder-32B,2e12b5f7bc878d424d222e224ed40aee564ec45f,float16,pretrained,Original,Qwen2ForCausalLM,33.2120108702677,FALSE,IFEval,0.436341130422834,43.6341130422834,BBH,0.640395506550809,48.5112134061417,MATH Level 5,0.305891238670695,30.5891238670695,GPQA,0.346476510067114,12.8635346756152,MUSR,0.4528125,15.8682291666667,MMLU-PRO,0.530252659574468,47.8058510638298,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-08,2024-12-10,1,Qwen/Qwen2.5-Coder-32B (Merge),apache-2.0,87,32,4.6902502672998 -Qwen/Qwen2.5-Coder-32B-Instruct_float16_b47205940b83b5b484577359f71ee7b88472df67_False,Qwen/Qwen2.5-Coder-32B-Instruct,b47205940b83b5b484577359f71ee7b88472df67,float16,chatmodels,Original,Qwen2ForCausalLM,38.7525412608276,FALSE,IFEval,0.726526726862503,72.6526726862503,BBH,0.662522222240513,52.2665152094361,MATH Level 5,0.427492447129909,42.7492447129909,GPQA,0.348993288590604,13.1991051454139,MUSR,0.438583333333333,13.7229166666667,MMLU-PRO,0.441323138297872,37.924793144208,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-06,2024-12-10,1,Qwen/Qwen2.5-Coder-32B-Instruct (Merge),apache-2.0,1294,32,4.69438966297979 -Qwen/Qwen2.5-Coder-7B_bfloat16_097b213c52760d22753af1aa5cbdba94b5c99506_True,Qwen/Qwen2.5-Coder-7B,097b213c52760d22753af1aa5cbdba94b5c99506,bfloat16,pretrained,Original,Qwen2ForCausalLM,19.2094905389622,TRUE,IFEval,0.344592348302504,34.4592348302504,BBH,0.485564055342148,28.4389441152555,MATH Level 5,0.191842900302115,19.1842900302115,GPQA,0.259228187919463,1.23042505592841,MUSR,0.344854166666667,2.1734375,MMLU-PRO,0.367935505319149,29.7706117021277,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-09-21,1,Qwen/Qwen2.5-Coder-7B (Merge),apache-2.0,79,7.616,2.30176716800796 -Qwen/Qwen2.5-Coder-7B-Instruct_bfloat16_3030861ab8e72c6155e1821631bf977ef40d3e5b_True,Qwen/Qwen2.5-Coder-7B-Instruct,3030861ab8e72c6155e1821631bf977ef40d3e5b,bfloat16,chatmodels,Original,Qwen2ForCausalLM,22.4254329651823,TRUE,IFEval,0.610147741326347,61.0147741326347,BBH,0.500797698622455,28.9385040453791,MATH Level 5,0.033987915407855,3.3987915407855,GPQA,0.291946308724832,5.59284116331097,MUSR,0.407270833333333,9.47552083333333,MMLU-PRO,0.335189494680851,26.1321660756501,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-11-07,1,Qwen/Qwen2.5-Coder-7B-Instruct (Merge),apache-2.0,356,7.616,1.77985748125157 -Qwen/Qwen2.5-Coder-7B-Instruct_float16_f784f10a7b2aac91bd26e6dbe7dccce691cd4ac5_True,Qwen/Qwen2.5-Coder-7B-Instruct,f784f10a7b2aac91bd26e6dbe7dccce691cd4ac5,float16,chatmodels,Original,Qwen2ForCausalLM,22.5245158164521,TRUE,IFEval,0.614718945730661,61.4718945730661,BBH,0.499904855031131,28.7265779689503,MATH Level 5,0.0309667673716012,3.09667673716012,GPQA,0.293624161073826,5.8165548098434,MUSR,0.4099375,9.87552083333333,MMLU-PRO,0.335438829787234,26.1598699763593,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-11-07,1,Qwen/Qwen2.5-Coder-7B-Instruct (Merge),apache-2.0,356,7.616,0.697647347897138 +Qwen/Qwen2.5-Coder-32B_float16_2e12b5f7bc878d424d222e224ed40aee564ec45f_False,Qwen/Qwen2.5-Coder-32B,2e12b5f7bc878d424d222e224ed40aee564ec45f,float16,pretrained,Original,Qwen2ForCausalLM,33.2120108702677,FALSE,IFEval,0.436341130422834,43.6341130422834,BBH,0.640395506550809,48.5112134061417,MATH Level 5,0.305891238670695,30.5891238670695,GPQA,0.346476510067114,12.8635346756152,MUSR,0.4528125,15.8682291666667,MMLU-PRO,0.530252659574468,47.8058510638298,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-08,2024-12-10,1,Qwen/Qwen2.5-Coder-32B (Merge),apache-2.0,88,32,4.6902502672998 +Qwen/Qwen2.5-Coder-32B-Instruct_float16_b47205940b83b5b484577359f71ee7b88472df67_False,Qwen/Qwen2.5-Coder-32B-Instruct,b47205940b83b5b484577359f71ee7b88472df67,float16,chatmodels,Original,Qwen2ForCausalLM,38.7525412608276,FALSE,IFEval,0.726526726862503,72.6526726862503,BBH,0.662522222240513,52.2665152094361,MATH Level 5,0.427492447129909,42.7492447129909,GPQA,0.348993288590604,13.1991051454139,MUSR,0.438583333333333,13.7229166666667,MMLU-PRO,0.441323138297872,37.924793144208,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-06,2024-12-10,1,Qwen/Qwen2.5-Coder-32B-Instruct (Merge),apache-2.0,1298,32,4.69438966297979 +Qwen/Qwen2.5-Coder-7B_bfloat16_097b213c52760d22753af1aa5cbdba94b5c99506_True,Qwen/Qwen2.5-Coder-7B,097b213c52760d22753af1aa5cbdba94b5c99506,bfloat16,pretrained,Original,Qwen2ForCausalLM,19.2094905389622,TRUE,IFEval,0.344592348302504,34.4592348302504,BBH,0.485564055342148,28.4389441152555,MATH Level 5,0.191842900302115,19.1842900302115,GPQA,0.259228187919463,1.23042505592841,MUSR,0.344854166666667,2.1734375,MMLU-PRO,0.367935505319149,29.7706117021277,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-09-21,1,Qwen/Qwen2.5-Coder-7B (Merge),apache-2.0,80,7.616,2.30176716800796 +Qwen/Qwen2.5-Coder-7B-Instruct_bfloat16_3030861ab8e72c6155e1821631bf977ef40d3e5b_True,Qwen/Qwen2.5-Coder-7B-Instruct,3030861ab8e72c6155e1821631bf977ef40d3e5b,bfloat16,chatmodels,Original,Qwen2ForCausalLM,22.4254329651823,TRUE,IFEval,0.610147741326347,61.0147741326347,BBH,0.500797698622455,28.9385040453791,MATH Level 5,0.033987915407855,3.3987915407855,GPQA,0.291946308724832,5.59284116331097,MUSR,0.407270833333333,9.47552083333333,MMLU-PRO,0.335189494680851,26.1321660756501,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-11-07,1,Qwen/Qwen2.5-Coder-7B-Instruct (Merge),apache-2.0,357,7.616,1.77985748125157 +Qwen/Qwen2.5-Coder-7B-Instruct_float16_f784f10a7b2aac91bd26e6dbe7dccce691cd4ac5_True,Qwen/Qwen2.5-Coder-7B-Instruct,f784f10a7b2aac91bd26e6dbe7dccce691cd4ac5,float16,chatmodels,Original,Qwen2ForCausalLM,22.5245158164521,TRUE,IFEval,0.614718945730661,61.4718945730661,BBH,0.499904855031131,28.7265779689503,MATH Level 5,0.0309667673716012,3.09667673716012,GPQA,0.293624161073826,5.8165548098434,MUSR,0.4099375,9.87552083333333,MMLU-PRO,0.335438829787234,26.1598699763593,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-11-07,1,Qwen/Qwen2.5-Coder-7B-Instruct (Merge),apache-2.0,357,7.616,0.697647347897138 Qwen/Qwen2.5-Math-72B-Instruct_bfloat16_3743c8fd46b002d105c1d28d180f1e531df1d40f_True,Qwen/Qwen2.5-Math-72B-Instruct,3743c8fd46b002d105c1d28d180f1e531df1d40f,bfloat16,chatmodels,Original,Qwen2ForCausalLM,29.6476372762452,TRUE,IFEval,0.400346635815193,40.0346635815193,BBH,0.645226663780376,48.9660960294212,MATH Level 5,0.193353474320242,19.3353474320242,GPQA,0.331375838926175,10.8501118568233,MUSR,0.447270833333333,16.3421875,MMLU-PRO,0.481216755319149,42.3574172576832,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-09-29,2,Qwen/Qwen2.5-72B,other,20,72.706,28.6768849752573 Qwen/Qwen2.5-Math-7B_bfloat16_8daf1d676c3f24ddec5a99c5cff00a5c0e1c441c_True,Qwen/Qwen2.5-Math-7B,8daf1d676c3f24ddec5a99c5cff00a5c0e1c441c,bfloat16,continuouslypretrained,Original,Qwen2ForCausalLM,17.8366571562897,TRUE,IFEval,0.245998395368733,24.5998395368733,BBH,0.445463937284094,22.0087606795866,MATH Level 5,0.305135951661631,30.5135951661631,GPQA,0.293624161073826,5.8165548098434,MUSR,0.37809375,4.99505208333333,MMLU-PRO,0.271775265957447,19.0861406619385,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-09-21,1,Qwen/Qwen2.5-7B,apache-2.0,20,7.616,1.33972974562764 Qwen/Qwen2.5-Math-7B-Instruct_bfloat16_b3b4c5794bf4b68c1978bb3525afc5e0d0d6fcc4_True,Qwen/Qwen2.5-Math-7B-Instruct,b3b4c5794bf4b68c1978bb3525afc5e0d0d6fcc4,bfloat16,chatmodels,Original,Qwen2ForCausalLM,16.5063129078039,TRUE,IFEval,0.263583957233474,26.3583957233474,BBH,0.438762734452786,21.489765755272,MATH Level 5,0.265105740181269,26.5105740181269,GPQA,0.261744966442953,1.56599552572707,MUSR,0.364729166666667,2.89114583333333,MMLU-PRO,0.281998005319149,20.2220005910165,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-19,2024-09-19,2,Qwen/Qwen2.5-7B,apache-2.0,40,7,1.13926656088631 @@ -764,7 +764,7 @@ RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2_bfloat16_fb0f72b9914a81892bfeea5a04fcd9676 SaisExperiments/Evil-Alpaca-3B-L3.2_float16_77d25b9182270a66ac60a91d646b447e1530f70e_False,SaisExperiments/Evil-Alpaca-3B-L3.2,77d25b9182270a66ac60a91d646b447e1530f70e,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,15.1125242410546,FALSE,IFEval,0.325108489917862,32.5108489917862,BBH,0.434075769922057,20.8519483855812,MATH Level 5,0.0657099697885197,6.57099697885197,GPQA,0.263422818791946,1.78970917225951,MUSR,0.419760416666667,10.93671875,MMLU-PRO,0.262134308510638,18.0149231678487,FALSE,FALSE,FALSE,FALSE,FALSE,2024-09-28,2024-09-28,1,SaisExperiments/Evil-Alpaca-3B-L3.2 (Merge),"",2,3.213,0.73314953595858 SaisExperiments/Gemma-2-2B-Opus-Instruct_bfloat16_7caa9e833d3f5713cf1b8ebd8beeb6ef02da99ea_False,SaisExperiments/Gemma-2-2B-Opus-Instruct,7caa9e833d3f5713cf1b8ebd8beeb6ef02da99ea,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,17.1956384886446,FALSE,IFEval,0.474959773401242,47.4959773401242,BBH,0.429284628144568,19.5295329945387,MATH Level 5,0.047583081570997,4.7583081570997,GPQA,0.283557046979866,4.47427293064877,MUSR,0.4056875,8.57760416666667,MMLU-PRO,0.265043218085106,18.3381353427896,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-03,2024-10-07,2,google/gemma-2-2b,gemma,0,2.614,1.1575938811599 SaisExperiments/Gemma-2-2B-Stheno-Filtered_bfloat16_683443cfa90c7a06978d1c5e9ead0fb0a68b49ca_False,SaisExperiments/Gemma-2-2B-Stheno-Filtered,683443cfa90c7a06978d1c5e9ead0fb0a68b49ca,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,15.4281621787742,FALSE,IFEval,0.419655403219014,41.9655403219014,BBH,0.414923415222218,17.4788672380534,MATH Level 5,0.0422960725075529,4.22960725075529,GPQA,0.27013422818792,2.68456375838927,MUSR,0.400291666666667,8.103125,MMLU-PRO,0.262965425531915,18.1072695035461,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-04,2024-10-08,2,google/gemma-2-2b,gemma,1,2.614,0.888367203586186 -Sakalti/magro-7B_float16_db8d1d3aa647ac59884448d23eef35187839f123_False,Sakalti/magro-7B,db8d1d3aa647ac59884448d23eef35187839f123,float16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,12.3825524996845,FALSE,IFEval,0.134390084974534,13.4390084974534,BBH,0.418552648596624,19.5488837610594,MATH Level 5,0.020392749244713,2.0392749244713,GPQA,0.295302013422819,6.04026845637584,MUSR,0.445989583333333,13.6153645833333,MMLU-PRO,0.276512632978723,19.6125147754137,TRUE,FALSE,FALSE,FALSE,FALSE,2024-12-11,2024-12-12,2,mistralai/Mistral-7B-v0.1,mit,0,7,0.452276006033254 +Sakalti/magro-7B_float16_db8d1d3aa647ac59884448d23eef35187839f123_False,Sakalti/magro-7B,db8d1d3aa647ac59884448d23eef35187839f123,float16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,12.3825524996845,FALSE,IFEval,0.134390084974534,13.4390084974534,BBH,0.418552648596624,19.5488837610594,MATH Level 5,0.020392749244713,2.0392749244713,GPQA,0.295302013422819,6.04026845637584,MUSR,0.445989583333333,13.6153645833333,MMLU-PRO,0.276512632978723,19.6125147754137,TRUE,FALSE,FALSE,FALSE,FALSE,2024-12-11,2024-12-12,2,mistralai/Mistral-7B-v0.1,mit,1,7,0.452276006033254 Salesforce/LLaMA-3-8B-SFR-Iterative-DPO-R_bfloat16_ad7d1aed82eb6d8ca4b3aad627ff76f72ab34f70_True,Salesforce/LLaMA-3-8B-SFR-Iterative-DPO-R,ad7d1aed82eb6d8ca4b3aad627ff76f72ab34f70,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,17.0297653902418,TRUE,IFEval,0.381562033183065,38.1562033183065,BBH,0.501195046966693,29.1502893497656,MATH Level 5,0.00151057401812689,0.151057401812689,GPQA,0.287751677852349,5.03355704697987,MUSR,0.363333333333333,5.55,MMLU-PRO,0.317237367021277,24.1374852245863,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-09,2024-07-02,0,Salesforce/LLaMA-3-8B-SFR-Iterative-DPO-R,llama3,76,8.03,0.857392430518302 SanjiWatsuki/Kunoichi-DPO-v2-7B_float16_5278247beb482c4fceff2294570236d68b74d132_True,SanjiWatsuki/Kunoichi-DPO-v2-7B,5278247beb482c4fceff2294570236d68b74d132,float16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,20.5564548887298,TRUE,IFEval,0.543103410063077,54.3103410063077,BBH,0.441559245086928,20.9034724841238,MATH Level 5,0.074773413897281,7.4773413897281,GPQA,0.296140939597315,6.15212527964205,MUSR,0.418833333333333,11.0875,MMLU-PRO,0.310671542553192,23.4079491725768,TRUE,FALSE,FALSE,FALSE,FALSE,2024-01-13,2024-06-28,0,SanjiWatsuki/Kunoichi-DPO-v2-7B,cc-by-nc-4.0,82,7.242,1.20820684318841 SanjiWatsuki/Silicon-Maid-7B_bfloat16_4e43d81f3fff1091df7cb2d85e9e306d25235701_True,SanjiWatsuki/Silicon-Maid-7B,4e43d81f3fff1091df7cb2d85e9e306d25235701,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,19.4498598838105,TRUE,IFEval,0.536783512192095,53.6783512192095,BBH,0.412797283100907,16.6927467535864,MATH Level 5,0.0672205438066465,6.72205438066465,GPQA,0.290268456375839,5.36912751677852,MUSR,0.418833333333333,11.0875,MMLU-PRO,0.308344414893617,23.1493794326241,TRUE,TRUE,FALSE,FALSE,FALSE,2023-12-27,2024-09-08,0,SanjiWatsuki/Silicon-Maid-7B,cc-by-4.0,104,7.242,0.606163302282549 @@ -819,7 +819,7 @@ T145/ZEUS-8B-V6_bfloat16_d7131128560dce428c3308ab46d7955b749c726d_True,T145/ZEUS T145/ZEUS-8B-V7_bfloat16_dbaa3828be77d925f40ecf3762b90ec4ad70e6d9_True,T145/ZEUS-8B-V7,dbaa3828be77d925f40ecf3762b90ec4ad70e6d9,bfloat16,chatmodels,Original,LlamaForCausalLM,28.4448455313931,TRUE,IFEval,0.778608536461035,77.8608536461035,BBH,0.507039411718064,29.55601639023,MATH Level 5,0.146525679758308,14.6525679758308,GPQA,0.296979865771812,6.26398210290828,MUSR,0.416166666666667,11.0875,MMLU-PRO,0.381233377659575,31.2481530732861,TRUE,TRUE,FALSE,FALSE,FALSE,2024-12-10,2024-12-11,1,T145/ZEUS-8B-V7 (Merge),llama3.1,0,8,0.655879471211826 T145/qwen-2.5-3B-merge-test_bfloat16_0d5f82d841f811fbf1ee07bfbf7c6eb1de812840_True,T145/qwen-2.5-3B-merge-test,0d5f82d841f811fbf1ee07bfbf7c6eb1de812840,bfloat16,chatmodels,Original,Qwen2ForCausalLM,21.1541505180996,TRUE,IFEval,0.575101840893274,57.5101840893274,BBH,0.484248874772039,27.8893413136761,MATH Level 5,0.0309667673716012,3.09667673716012,GPQA,0.285234899328859,4.6979865771812,MUSR,0.400729166666667,8.29114583333333,MMLU-PRO,0.328956117021277,25.4395685579196,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-11-16,0,Removed,"",0,3.397,0.783956586523256 THUDM/glm-4-9b_bfloat16_99a140996f9d4f197842fb6b1aab217a42e27ef3_False,THUDM/glm-4-9b,99a140996f9d4f197842fb6b1aab217a42e27ef3,bfloat16,pretrained,Original,ChatGLMModelM,18.0067317317162,FALSE,IFEval,0.142608279365417,14.2608279365417,BBH,0.552836814166527,35.8112835812089,MATH Level 5,0,0,GPQA,0.316275167785235,8.83668903803132,MUSR,0.438583333333333,14.1895833333333,MMLU-PRO,0.414478058510638,34.942006501182,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-04,2024-07-04,0,THUDM/glm-4-9b,other,113,9,1.67244683755118 -THUDM/glm-4-9b-chat_bfloat16_04419001bc63e05e70991ade6da1f91c4aeec278_True,THUDM/glm-4-9b-chat,04419001bc63e05e70991ade6da1f91c4aeec278,bfloat16,chatmodels,Original,ChatGLMModelM,10.9734772970452,TRUE,IFEval,0,0,BBH,0.473638842910357,25.2051836744402,MATH Level 5,0,0,GPQA,0.313758389261745,8.50111856823266,MUSR,0.399427083333333,8.06171875,MMLU-PRO,0.316655585106383,24.0728427895981,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-04,2024-07-09,0,THUDM/glm-4-9b-chat,other,640,9,0.247134508492731 +THUDM/glm-4-9b-chat_bfloat16_04419001bc63e05e70991ade6da1f91c4aeec278_True,THUDM/glm-4-9b-chat,04419001bc63e05e70991ade6da1f91c4aeec278,bfloat16,chatmodels,Original,ChatGLMModelM,10.9734772970452,TRUE,IFEval,0,0,BBH,0.473638842910357,25.2051836744402,MATH Level 5,0,0,GPQA,0.313758389261745,8.50111856823266,MUSR,0.399427083333333,8.06171875,MMLU-PRO,0.316655585106383,24.0728427895981,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-04,2024-07-09,0,THUDM/glm-4-9b-chat,other,641,9,0.247134508492731 THUDM/glm-4-9b-chat-1m_bfloat16_0aa722c7e0745dd21453427dd44c257dd253304f_True,THUDM/glm-4-9b-chat-1m,0aa722c7e0745dd21453427dd44c257dd253304f,bfloat16,chatmodels,Original,ChatGLMModel,8.92251018653198,TRUE,IFEval,0,0,BBH,0.418005782183303,17.1080285081681,MATH Level 5,0,0,GPQA,0.303691275167785,7.15883668903803,MUSR,0.379458333333333,5.23229166666667,MMLU-PRO,0.316323138297872,24.0359042553192,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-04,2024-10-09,0,THUDM/glm-4-9b-chat-1m,other,181,9.484,0.205669954986166 TIGER-Lab/MAmmoTH2-7B-Plus_bfloat16_3ed578d8dda09787137e363a0dc32e3a8ed908de_True,TIGER-Lab/MAmmoTH2-7B-Plus,3ed578d8dda09787137e363a0dc32e3a8ed908de,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,21.4698622596292,TRUE,IFEval,0.557466411344123,55.7466411344123,BBH,0.423469498880191,18.9259532275557,MATH Level 5,0.175981873111782,17.5981873111782,GPQA,0.280201342281879,4.0268456375839,MUSR,0.412354166666667,10.1109375,MMLU-PRO,0.301695478723404,22.4106087470449,TRUE,FALSE,FALSE,FALSE,FALSE,2024-05-06,2024-06-27,0,TIGER-Lab/MAmmoTH2-7B-Plus,mit,6,7.242,0.552663350555736 TTTXXX01/Mistral-7B-Base-SimPO2-5e-7_bfloat16_7a271e3061165f4e1abfe26715c04e20c2ac935e_True,TTTXXX01/Mistral-7B-Base-SimPO2-5e-7,7a271e3061165f4e1abfe26715c04e20c2ac935e,bfloat16,chatmodels,Original,MistralForCausalLM,16.3796884014764,TRUE,IFEval,0.439189129288067,43.9189129288067,BBH,0.431955150148828,20.6926273825575,MATH Level 5,0.0241691842900302,2.41691842900302,GPQA,0.297818791946309,6.3758389261745,MUSR,0.360416666666667,5.25208333333333,MMLU-PRO,0.276595744680851,19.6217494089835,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-30,2024-09-01,2,mistralai/Mistral-7B-v0.1,apache-2.0,0,7.242,0.522996132267287 @@ -967,7 +967,7 @@ adamo1139/Yi-34B-200K-AEZAKMI-v2_float16_189b42b0dae6352fbe7165255aae851961c8e67 adriszmar/QAIMath-Qwen2.5-7B-TIES_float16_c89bc166dbe2a31c1fceb40ea7acdd96c5620ff5_False,adriszmar/QAIMath-Qwen2.5-7B-TIES,c89bc166dbe2a31c1fceb40ea7acdd96c5620ff5,float16,basemergesandmoerges,Original,Qwen2ForCausalLM,5.46954201663263,FALSE,IFEval,0.174632198123202,17.4632198123202,BBH,0.312637953839658,5.25369060603348,MATH Level 5,0,0,GPQA,0.24496644295302,0,MUSR,0.40959375,9.13255208333333,MMLU-PRO,0.108710106382979,0.967789598108746,TRUE,TRUE,FALSE,FALSE,FALSE,2024-10-27,2024-10-27,0,adriszmar/QAIMath-Qwen2.5-7B-TIES,apache-2.0,0,7.616,1.28340822238651 adriszmar/QAIMath-Qwen2.5-7B-TIES_bfloat16_c89bc166dbe2a31c1fceb40ea7acdd96c5620ff5_False,adriszmar/QAIMath-Qwen2.5-7B-TIES,c89bc166dbe2a31c1fceb40ea7acdd96c5620ff5,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,4.96326543344731,FALSE,IFEval,0.16853725891745,16.853725891745,BBH,0.312426882748846,5.01915128340691,MATH Level 5,0,0,GPQA,0.249161073825503,0,MUSR,0.396291666666667,7.16979166666667,MMLU-PRO,0.106632313829787,0.736923758865247,TRUE,TRUE,FALSE,FALSE,FALSE,2024-10-27,2024-10-27,0,adriszmar/QAIMath-Qwen2.5-7B-TIES,apache-2.0,0,7.616,1.30631586113994 ahmeda335/13_outOf_32_pruned_layers_llama3.1-8b_float16_248c420cc0a0bb8fce3a64a998ca0ce89613783c_True,ahmeda335/13_outOf_32_pruned_layers_llama3.1-8b,248c420cc0a0bb8fce3a64a998ca0ce89613783c,float16,chatmodels,Original,LlamaForCausalLM,4.40425862219458,TRUE,IFEval,0.174807289104022,17.4807289104022,BBH,0.288325776026615,1.67784524024114,MATH Level 5,0,0,GPQA,0.259228187919463,1.23042505592841,MUSR,0.380322916666667,4.60703125,MMLU-PRO,0.112865691489362,1.42952127659574,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-21,2024-12-03,1,ahmeda335/13_outOf_32_pruned_layers_llama3.1-8b (Merge),apache-2.0,0,5.195,0.496023692057088 -ai21labs/Jamba-v0.1_bfloat16_ce13f3fe99555a2606d1892665bb67649032ff2d_True,ai21labs/Jamba-v0.1,ce13f3fe99555a2606d1892665bb67649032ff2d,bfloat16,pretrained,Original,JambaForCausalLM,9.14283638861454,TRUE,IFEval,0.202559209563957,20.2559209563957,BBH,0.360226024516457,10.7220589188703,MATH Level 5,0.0113293051359517,1.13293051359517,GPQA,0.268456375838926,2.46085011185682,MUSR,0.359020833333333,3.7109375,MMLU-PRO,0.249168882978723,16.5743203309693,TRUE,FALSE,TRUE,FALSE,TRUE,2024-03-28,2024-09-16,0,ai21labs/Jamba-v0.1,apache-2.0,1172,51.57,10.1121426069674 +ai21labs/Jamba-v0.1_bfloat16_ce13f3fe99555a2606d1892665bb67649032ff2d_True,ai21labs/Jamba-v0.1,ce13f3fe99555a2606d1892665bb67649032ff2d,bfloat16,pretrained,Original,JambaForCausalLM,9.14283638861454,TRUE,IFEval,0.202559209563957,20.2559209563957,BBH,0.360226024516457,10.7220589188703,MATH Level 5,0.0113293051359517,1.13293051359517,GPQA,0.268456375838926,2.46085011185682,MUSR,0.359020833333333,3.7109375,MMLU-PRO,0.249168882978723,16.5743203309693,TRUE,FALSE,TRUE,FALSE,TRUE,2024-03-28,2024-09-16,0,ai21labs/Jamba-v0.1,apache-2.0,1173,51.57,10.1121426069674 aixonlab/Aether-12b_float16_c55d08a69c74f87c18ab5afb05d46359f389c91a_False,aixonlab/Aether-12b,c55d08a69c74f87c18ab5afb05d46359f389c91a,float16,basemergesandmoerges,Original,MistralForCausalLM,17.8822973516558,FALSE,IFEval,0.234682863690563,23.4682863690563,BBH,0.517940075043548,30.5511383113031,MATH Level 5,0.0966767371601209,9.66767371601209,GPQA,0.316275167785235,8.83668903803132,MUSR,0.382864583333333,7.99140625,MMLU-PRO,0.341007313829787,26.7785904255319,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-24,2024-10-09,1,Xclbr7/Arcanum-12b,apache-2.0,1,12.248,1.86643205080331 aixonlab/Grey-12b_float16_50f56572870c49186c3679f9949a602d2d97c046_False,aixonlab/Grey-12b,50f56572870c49186c3679f9949a602d2d97c046,float16,basemergesandmoerges,Original,MistralForCausalLM,23.606024116142,FALSE,IFEval,0.396799381197445,39.6799381197445,BBH,0.569895750595983,38.7460434549176,MATH Level 5,0.0936555891238671,9.36555891238671,GPQA,0.300335570469799,6.71140939597315,MUSR,0.451635416666667,16.2544270833333,MMLU-PRO,0.377908909574468,30.8787677304965,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-07,2024-10-09,2,Xclbr7/Arcanum-12b,apache-2.0,0,12.248,1.46869366755381 akjindal53244/Llama-3.1-Storm-8B_bfloat16_df21b06dcf534b026dd301a44a521d7253c8b94b_True,akjindal53244/Llama-3.1-Storm-8B,df21b06dcf534b026dd301a44a521d7253c8b94b,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,29.3652497717672,TRUE,IFEval,0.803263119633683,80.3263119633683,BBH,0.519633040287071,31.6156951138501,MATH Level 5,0.16238670694864,16.238670694864,GPQA,0.309563758389262,7.94183445190157,MUSR,0.402833333333333,8.82083333333334,MMLU-PRO,0.381233377659575,31.2481530732861,TRUE,TRUE,FALSE,FALSE,FALSE,2024-08-12,2024-10-27,0,akjindal53244/Llama-3.1-Storm-8B,llama3.1,168,8.03,0.794391488777388 @@ -979,9 +979,9 @@ allenai/Llama-3.1-Tulu-3-70B-DPO_bfloat16_6ea110f39fb660573111892a1381d3be3f826f allenai/Llama-3.1-Tulu-3-70B-SFT_bfloat16_f58ab66db3a1c5dd805c6d3420b2b4f5aef30041_True,allenai/Llama-3.1-Tulu-3-70B-SFT,f58ab66db3a1c5dd805c6d3420b2b4f5aef30041,bfloat16,chatmodels,Original,LlamaForCausalLM,38.7226108999501,TRUE,IFEval,0.805061680784762,80.5061680784762,BBH,0.595143780058093,42.0239839490646,MATH Level 5,0.324018126888218,32.4018126888218,GPQA,0.344798657718121,12.6398210290828,MUSR,0.502614583333333,24.4934895833333,MMLU-PRO,0.462433510638298,40.270390070922,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-18,2024-11-27,1,allenai/Llama-3.1-Tulu-3-70B-SFT (Merge),llama3.1,4,70.554,27.3383271895368 allenai/Llama-3.1-Tulu-3-8B_bfloat16_63b75e0dd6eac3725319f869716b9b70c16a6a65_True,allenai/Llama-3.1-Tulu-3-8B,63b75e0dd6eac3725319f869716b9b70c16a6a65,bfloat16,chatmodels,Original,LlamaForCausalLM,26.0349980816721,TRUE,IFEval,0.826668794354535,82.6668794354535,BBH,0.404983310273191,16.671812993248,MATH Level 5,0.196374622356495,19.6374622356495,GPQA,0.298657718120805,6.48769574944072,MUSR,0.41746875,10.4502604166667,MMLU-PRO,0.28266289893617,20.2958776595745,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-20,2024-11-21,1,allenai/Llama-3.1-Tulu-3-8B (Merge),llama3.1,98,8.03,0.703774148994329 allenai/Llama-3.1-Tulu-3-8B_float16_50fef8756a9a4ca2010587d128aebb3a18ec897d_True,allenai/Llama-3.1-Tulu-3-8B,50fef8756a9a4ca2010587d128aebb3a18ec897d,float16,chatmodels,Original,LlamaForCausalLM,25.8832245109219,TRUE,IFEval,0.825469753587149,82.5469753587149,BBH,0.40608256120952,16.8580520694028,MATH Level 5,0.188821752265861,18.8821752265861,GPQA,0.296979865771812,6.26398210290828,MUSR,0.41746875,10.5169270833333,MMLU-PRO,0.282081117021277,20.2312352245863,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-20,2024-11-28,1,allenai/Llama-3.1-Tulu-3-8B (Merge),llama3.1,98,8.03,0.701232116583257 -allenai/Llama-3.1-Tulu-3-8B-DPO_bfloat16_002347006131d85678ea3865520bc9caad69869a_True,allenai/Llama-3.1-Tulu-3-8B-DPO,002347006131d85678ea3865520bc9caad69869a,bfloat16,chatmodels,Original,LlamaForCausalLM,25.6205762082762,TRUE,IFEval,0.802938425599631,80.2938425599631,BBH,0.407942855704415,17.4260162269845,MATH Level 5,0.185800604229607,18.5800604229607,GPQA,0.293624161073826,5.8165548098434,MUSR,0.416135416666667,10.5169270833333,MMLU-PRO,0.289810505319149,21.0900561465721,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-20,2024-11-22,1,allenai/Llama-3.1-Tulu-3-8B-DPO (Merge),llama3.1,13,8,0.670337573364492 +allenai/Llama-3.1-Tulu-3-8B-DPO_bfloat16_002347006131d85678ea3865520bc9caad69869a_True,allenai/Llama-3.1-Tulu-3-8B-DPO,002347006131d85678ea3865520bc9caad69869a,bfloat16,chatmodels,Original,LlamaForCausalLM,25.6205762082762,TRUE,IFEval,0.802938425599631,80.2938425599631,BBH,0.407942855704415,17.4260162269845,MATH Level 5,0.185800604229607,18.5800604229607,GPQA,0.293624161073826,5.8165548098434,MUSR,0.416135416666667,10.5169270833333,MMLU-PRO,0.289810505319149,21.0900561465721,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-20,2024-11-22,1,allenai/Llama-3.1-Tulu-3-8B-DPO (Merge),llama3.1,14,8,0.670337573364492 allenai/Llama-3.1-Tulu-3-8B-RM_bfloat16_76247c00745747f820f1712949b5b37901d0f9c4_True,allenai/Llama-3.1-Tulu-3-8B-RM,76247c00745747f820f1712949b5b37901d0f9c4,bfloat16,chatmodels,Original,LlamaForSequenceClassification,4.23505701818803,TRUE,IFEval,0.167013524116012,16.7013524116012,BBH,0.29500411474705,2.64966998137355,MATH Level 5,0,0,GPQA,0.256711409395973,0.894854586129753,MUSR,0.376416666666667,4.25208333333334,MMLU-PRO,0.108211436170213,0.912381796690307,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-20,2024-11-22,1,allenai/Llama-3.1-Tulu-3-8B-RM (Merge),llama3.1,7,8,0.73689906762706 -allenai/Llama-3.1-Tulu-3-8B-SFT_bfloat16_4ddd761e6750e04ea3d468175f78463628bba860_True,allenai/Llama-3.1-Tulu-3-8B-SFT,4ddd761e6750e04ea3d468175f78463628bba860,bfloat16,chatmodels,Original,LlamaForCausalLM,22.5339999676641,TRUE,IFEval,0.740340075444266,74.0340075444266,BBH,0.387186327050165,13.9312081682626,MATH Level 5,0.11404833836858,11.404833836858,GPQA,0.277684563758389,3.69127516778523,MUSR,0.426770833333333,12.0130208333333,MMLU-PRO,0.281166888297872,20.1296542553192,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-18,2024-11-22,1,allenai/Llama-3.1-Tulu-3-8B-SFT (Merge),llama3.1,14,8.03,0.683246279517383 +allenai/Llama-3.1-Tulu-3-8B-SFT_bfloat16_4ddd761e6750e04ea3d468175f78463628bba860_True,allenai/Llama-3.1-Tulu-3-8B-SFT,4ddd761e6750e04ea3d468175f78463628bba860,bfloat16,chatmodels,Original,LlamaForCausalLM,22.5339999676641,TRUE,IFEval,0.740340075444266,74.0340075444266,BBH,0.387186327050165,13.9312081682626,MATH Level 5,0.11404833836858,11.404833836858,GPQA,0.277684563758389,3.69127516778523,MUSR,0.426770833333333,12.0130208333333,MMLU-PRO,0.281166888297872,20.1296542553192,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-18,2024-11-22,1,allenai/Llama-3.1-Tulu-3-8B-SFT (Merge),llama3.1,15,8.03,0.683246279517383 allenai/OLMo-1B-hf_bfloat16_8e995430edd24416ccfa98b5b283fa07b0c9f1a9_False,allenai/OLMo-1B-hf,8e995430edd24416ccfa98b5b283fa07b0c9f1a9,bfloat16,pretrained,Original,OlmoForCausalLM,6.47027844039243,FALSE,IFEval,0.218196607224387,21.8196607224387,BBH,0.305194689884293,3.19654631243032,MATH Level 5,0.00755287009063444,0.755287009063444,GPQA,0.261744966442953,1.56599552572707,MUSR,0.40978125,9.55598958333333,MMLU-PRO,0.117353723404255,1.9281914893617,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-12,2024-06-12,0,allenai/OLMo-1B-hf,apache-2.0,17,1.177,0.248873749951744 allenai/OLMo-7B-Instruct-hf_bfloat16_2ea947518df93433aa71219f29b36c72ac63be95_True,allenai/OLMo-7B-Instruct-hf,2ea947518df93433aa71219f29b36c72ac63be95,bfloat16,chatmodels,Original,OlmoForCausalLM,10.7608566037124,TRUE,IFEval,0.347265256186917,34.7265256186917,BBH,0.370646986666272,13.159933415267,MATH Level 5,0.00830815709969789,0.830815709969789,GPQA,0.270973154362416,2.79642058165548,MUSR,0.376479166666667,4.3265625,MMLU-PRO,0.178523936170213,8.72488179669031,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-04,2024-06-27,0,allenai/OLMo-7B-Instruct-hf,apache-2.0,2,7,1.19995072912062 allenai/OLMo-7B-hf_bfloat16_687d934d36a05417048d0fe7482f24f389fef6aa_False,allenai/OLMo-7B-hf,687d934d36a05417048d0fe7482f24f389fef6aa,bfloat16,pretrained,Original,OlmoForCausalLM,6.77615120977129,FALSE,IFEval,0.271927374920766,27.1927374920766,BBH,0.327913165873623,5.76198704108083,MATH Level 5,0.006797583081571,0.6797583081571,GPQA,0.272651006711409,3.02013422818792,MUSR,0.348666666666667,2.08333333333333,MMLU-PRO,0.117270611702128,1.91895685579196,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-12,2024-06-27,0,allenai/OLMo-7B-hf,apache-2.0,12,6.888,0.590564158425061 @@ -1079,7 +1079,7 @@ allura-org/MS-Meadowlark-22B_bfloat16_6eb2f6bee66dbffa1b17397e75a7380ed4f9d0ac_T allura-org/MoE-Girl-1BA-7BT_bfloat16_ecfac73ab9e7f2ee006d6a2ad9c8e86a85deab2b_True,allura-org/MoE-Girl-1BA-7BT,ecfac73ab9e7f2ee006d6a2ad9c8e86a85deab2b,bfloat16,fine-tunedondomain-specificdatasets,Original,OlmoeForCausalLM,6.39021099096268,TRUE,IFEval,0.270503375488149,27.0503375488149,BBH,0.313917536326241,4.8423440285205,MATH Level 5,0.0143504531722054,1.43504531722054,GPQA,0.258389261744966,1.11856823266219,MUSR,0.343552083333333,1.47734375,MMLU-PRO,0.121758643617021,2.41762706855792,TRUE,FALSE,TRUE,FALSE,FALSE,2024-10-08,2024-10-10,1,allenai/OLMoE-1B-7B-0924,apache-2.0,13,6.919,3.20115464710205 aloobun/Meta-Llama-3-7B-28Layers_bfloat16_9822e6b8d4de0c0f2964d299f6fcef72385a0341_False,aloobun/Meta-Llama-3-7B-28Layers,9822e6b8d4de0c0f2964d299f6fcef72385a0341,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,13.1365160784577,FALSE,IFEval,0.196364534989384,19.6364534989384,BBH,0.443749701425339,22.0965302513435,MATH Level 5,0.013595166163142,1.3595166163142,GPQA,0.294463087248322,5.92841163310962,MUSR,0.358927083333333,5.79921875,MMLU-PRO,0.315990691489362,23.9989657210402,TRUE,TRUE,FALSE,FALSE,FALSE,2024-05-10,2024-06-26,1,aloobun/Meta-Llama-3-7B-28Layers (Merge),llama3,0,7.158,0.809358294835876 aloobun/d-SmolLM2-360M_bfloat16_2a1d82b4cbcdfdff3c2cfcd171435c5f01b8de43_False,aloobun/d-SmolLM2-360M,2a1d82b4cbcdfdff3c2cfcd171435c5f01b8de43,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,6.00783726880815,FALSE,IFEval,0.209703586483863,20.9703586483863,BBH,0.319578440563683,4.76282074716569,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.253355704697987,0.447427293064876,MUSR,0.3980625,7.7578125,MMLU-PRO,0.116938164893617,1.882018321513,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-20,2024-11-26,0,aloobun/d-SmolLM2-360M,apache-2.0,1,0.362,0.370123277612295 -alpindale/WizardLM-2-8x22B_bfloat16_087834da175523cffd66a7e19583725e798c1b4f_False,alpindale/WizardLM-2-8x22B,087834da175523cffd66a7e19583725e798c1b4f,bfloat16,fine-tunedondomain-specificdatasets,Original,MixtralForCausalLM,32.983523136833,FALSE,IFEval,0.527216673980594,52.7216673980594,BBH,0.63773079389171,48.5761681793627,MATH Level 5,0.245468277945619,24.5468277945619,GPQA,0.381711409395973,17.5615212527964,MUSR,0.438708333333333,14.5385416666667,MMLU-PRO,0.459607712765958,39.9564125295508,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-16,2024-06-28,0,alpindale/WizardLM-2-8x22B,apache-2.0,389,140.621,93.3052216637186 +alpindale/WizardLM-2-8x22B_bfloat16_087834da175523cffd66a7e19583725e798c1b4f_False,alpindale/WizardLM-2-8x22B,087834da175523cffd66a7e19583725e798c1b4f,bfloat16,fine-tunedondomain-specificdatasets,Original,MixtralForCausalLM,32.983523136833,FALSE,IFEval,0.527216673980594,52.7216673980594,BBH,0.63773079389171,48.5761681793627,MATH Level 5,0.245468277945619,24.5468277945619,GPQA,0.381711409395973,17.5615212527964,MUSR,0.438708333333333,14.5385416666667,MMLU-PRO,0.459607712765958,39.9564125295508,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-16,2024-06-28,0,alpindale/WizardLM-2-8x22B,apache-2.0,390,140.621,93.3052216637186 alpindale/magnum-72b-v1_bfloat16_fef27e0f235ae8858b84b765db773a2a954110dd_True,alpindale/magnum-72b-v1,fef27e0f235ae8858b84b765db773a2a954110dd,bfloat16,chatmodels,Original,Qwen2ForCausalLM,42.5765874746874,TRUE,IFEval,0.760648412877831,76.0648412877831,BBH,0.698221579437321,57.6531848551427,MATH Level 5,0.376888217522659,37.6888217522659,GPQA,0.390939597315436,18.7919463087248,MUSR,0.4489375,15.6171875,MMLU-PRO,0.546791888297872,49.643543144208,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-17,2024-07-25,2,Qwen/Qwen2-72B,other,160,72.706,12.5151227050283 altomek/YiSM-34B-0rn_float16_7a481c67cbdd5c846d6aaab5ef9f1eebfad812c2_True,altomek/YiSM-34B-0rn,7a481c67cbdd5c846d6aaab5ef9f1eebfad812c2,float16,basemergesandmoerges,Original,LlamaForCausalLM,30.4742480578893,TRUE,IFEval,0.428373382624769,42.8373382624769,BBH,0.614000957386887,45.3829272490071,MATH Level 5,0.22583081570997,22.583081570997,GPQA,0.371644295302013,16.2192393736018,MUSR,0.445,14.7583333333333,MMLU-PRO,0.469581117021277,41.0645685579196,TRUE,TRUE,FALSE,FALSE,FALSE,2024-05-26,2024-06-27,1,altomek/YiSM-34B-0rn (Merge),apache-2.0,1,34.389,2.96062414416228 amazon/MegaBeam-Mistral-7B-300k_bfloat16_42572e5c9a0747b19af5c5c9962d122622f32295_True,amazon/MegaBeam-Mistral-7B-300k,42572e5c9a0747b19af5c5c9962d122622f32295,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,17.0728229713939,TRUE,IFEval,0.520347123410329,52.0347123410329,BBH,0.422773173111297,19.291805959592,MATH Level 5,0.0241691842900302,2.41691842900302,GPQA,0.273489932885906,3.13199105145414,MUSR,0.398,8.35,MMLU-PRO,0.254903590425532,17.2115100472813,TRUE,FALSE,FALSE,FALSE,FALSE,2024-05-13,2024-10-07,0,amazon/MegaBeam-Mistral-7B-300k,apache-2.0,15,7.242,0.649609938368253 @@ -1087,7 +1087,7 @@ amd/AMD-Llama-135m_float16_8f9c39b5ed86d422ab332ed1ecf042fdaeb57903_False,amd/AM amd/AMD-Llama-135m_bfloat16_8f9c39b5ed86d422ab332ed1ecf042fdaeb57903_False,amd/AMD-Llama-135m,8f9c39b5ed86d422ab332ed1ecf042fdaeb57903,bfloat16,pretrained,Original,LlamaForCausalLM,5.19121220850702,FALSE,IFEval,0.191843198269481,19.1843198269481,BBH,0.296944497487803,2.53795268047751,MATH Level 5,0.00528700906344411,0.528700906344411,GPQA,0.258389261744966,1.11856823266219,MUSR,0.384572916666667,5.90494791666667,MMLU-PRO,0.116855053191489,1.87278368794326,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-19,2024-10-01,0,amd/AMD-Llama-135m,apache-2.0,110,0.134,0.525707283316026 anakin87/gemma-2b-orpo_bfloat16_bf6bfe30c31c18620767ad60d0bff89343804230_True,anakin87/gemma-2b-orpo,bf6bfe30c31c18620767ad60d0bff89343804230,bfloat16,chatmodels,Original,GemmaForCausalLM,7.18400129408368,TRUE,IFEval,0.247796956519812,24.7796956519812,BBH,0.342617094356178,7.94944502776896,MATH Level 5,0.0128398791540785,1.28398791540785,GPQA,0.261744966442953,1.56599552572707,MUSR,0.372760416666667,4.12838541666667,MMLU-PRO,0.130568484042553,3.39649822695035,TRUE,FALSE,FALSE,FALSE,FALSE,2024-03-24,2024-07-06,1,google/gemma-2b,other,28,2.506,0.789926565520433 anthracite-org/magnum-v1-72b_bfloat16_f8f85021bace7e8250ed8559c5b78b8b34f0c4cc_True,anthracite-org/magnum-v1-72b,f8f85021bace7e8250ed8559c5b78b8b34f0c4cc,bfloat16,chatmodels,Original,Qwen2ForCausalLM,42.6104477977765,TRUE,IFEval,0.760648412877831,76.0648412877831,BBH,0.698221579437321,57.6531848551427,MATH Level 5,0.376888217522659,37.6888217522659,GPQA,0.390939597315436,18.7919463087248,MUSR,0.4489375,15.6171875,MMLU-PRO,0.548620345744681,49.8467050827423,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-17,2024-09-21,2,Qwen/Qwen2-72B,other,160,72.706,12.891056208981 -anthracite-org/magnum-v2-12b_bfloat16__True,anthracite-org/magnum-v2-12b,"",bfloat16,chatmodels,Original,MistralForCausalLM,18.6951166288168,TRUE,IFEval,0.376166349729828,37.6166349729828,BBH,0.502086401320011,28.7855515953659,MATH Level 5,0.0483383685800604,4.83383685800604,GPQA,0.291107382550336,5.48098434004475,MUSR,0.41790625,11.3716145833333,MMLU-PRO,0.316738696808511,24.0820774231679,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-03,2024-09-05,1,mistralai/Mistral-Nemo-Base-2407,apache-2.0,80,12.248,1.64883538788882 +anthracite-org/magnum-v2-12b_bfloat16__True,anthracite-org/magnum-v2-12b,"",bfloat16,chatmodels,Original,MistralForCausalLM,18.6951166288168,TRUE,IFEval,0.376166349729828,37.6166349729828,BBH,0.502086401320011,28.7855515953659,MATH Level 5,0.0483383685800604,4.83383685800604,GPQA,0.291107382550336,5.48098434004475,MUSR,0.41790625,11.3716145833333,MMLU-PRO,0.316738696808511,24.0820774231679,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-03,2024-09-05,1,mistralai/Mistral-Nemo-Base-2407,apache-2.0,81,12.248,1.64883538788882 anthracite-org/magnum-v2-72b_bfloat16_c9c5826ef42b9fcc8a8e1079be574481cf0b6cc6_True,anthracite-org/magnum-v2-72b,c9c5826ef42b9fcc8a8e1079be574481cf0b6cc6,bfloat16,chatmodels,Original,Qwen2ForCausalLM,41.5562861642026,TRUE,IFEval,0.756027340789106,75.6027340789106,BBH,0.700507651412952,57.854704320851,MATH Level 5,0.340634441087613,34.0634441087613,GPQA,0.385906040268456,18.1208053691275,MUSR,0.4371875,14.1817708333333,MMLU-PRO,0.545628324468085,49.5142582742317,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-18,2024-09-05,2,Qwen/Qwen2-72B,other,33,72.706,12.1342168551245 anthracite-org/magnum-v2.5-12b-kto_float16_aee0374e5a43e950c9977b0004dede1c57be2999_True,anthracite-org/magnum-v2.5-12b-kto,aee0374e5a43e950c9977b0004dede1c57be2999,float16,chatmodels,Original,MistralForCausalLM,18.8820850550188,TRUE,IFEval,0.386557666990253,38.6557666990253,BBH,0.507696118625434,29.625059445981,MATH Level 5,0.0460725075528701,4.60725075528701,GPQA,0.293624161073826,5.8165548098434,MUSR,0.408635416666667,9.97942708333334,MMLU-PRO,0.321476063829787,24.608451536643,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-12,2024-08-29,2,mistralai/Mistral-Nemo-Base-2407,apache-2.0,42,12.248,1.60906305088813 anthracite-org/magnum-v3-27b-kto_bfloat16_96fbb750b3150e5fe9d6d2fcf757f49310d99a43_True,anthracite-org/magnum-v3-27b-kto,96fbb750b3150e5fe9d6d2fcf757f49310d99a43,bfloat16,chatmodels,Original,Gemma2ForCausalLM,29.0979057982708,TRUE,IFEval,0.567483166886085,56.7483166886085,BBH,0.586040577894583,41.1601029248443,MATH Level 5,0.166918429003021,16.6918429003021,GPQA,0.355704697986577,14.0939597315436,MUSR,0.38546875,9.91692708333333,MMLU-PRO,0.423786569148936,35.9762854609929,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-06,2024-09-15,1,anthracite-org/magnum-v3-27b-kto (Merge),gemma,11,27.227,3.93753396148653 @@ -1098,14 +1098,14 @@ anthracite-org/magnum-v4-12b_bfloat16_704f2ccfe662052e415499e56789dd88ec01a113_F anthracite-org/magnum-v4-22b_bfloat16_e5239e71d2628269b453a832de98c1ecb79d2557_False,anthracite-org/magnum-v4-22b,e5239e71d2628269b453a832de98c1ecb79d2557,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,27.7159004280105,FALSE,IFEval,0.56286209479736,56.286209479736,BBH,0.548612004937422,35.5491485327735,MATH Level 5,0.191842900302115,19.1842900302115,GPQA,0.328020134228188,10.4026845637584,MUSR,0.44078125,13.4309895833333,MMLU-PRO,0.382978723404255,31.4420803782506,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-20,2024-10-23,0,anthracite-org/magnum-v4-22b,other,16,22.247,1.65029003573429 anthracite-org/magnum-v4-27b_bfloat16_50a14716bdeb6a9376b9377df31ab1497864f3f9_False,anthracite-org/magnum-v4-27b,50a14716bdeb6a9376b9377df31ab1497864f3f9,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,26.3308890010956,FALSE,IFEval,0.345416827351428,34.5416827351428,BBH,0.586729810989139,40.9603843335009,MATH Level 5,0.161631419939577,16.1631419939577,GPQA,0.36996644295302,15.9955257270693,MUSR,0.437989583333333,12.8153645833333,MMLU-PRO,0.437583111702128,37.5092346335697,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-20,2024-10-23,0,anthracite-org/magnum-v4-27b,gemma,10,27.227,5.73635389356619 anthracite-org/magnum-v4-9b_bfloat16_e9db6cb80f02ca2e2db4538ef59f7a30f69a849d_False,anthracite-org/magnum-v4-9b,e9db6cb80f02ca2e2db4538ef59f7a30f69a849d,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,23.7738183884644,FALSE,IFEval,0.350262858105383,35.0262858105383,BBH,0.533642399193156,33.2704044364764,MATH Level 5,0.129154078549849,12.9154078549849,GPQA,0.347315436241611,12.9753914988814,MUSR,0.451572916666667,15.6466145833333,MMLU-PRO,0.395279255319149,32.8088061465721,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-20,2024-10-23,0,anthracite-org/magnum-v4-9b,gemma,11,9.242,2.55632615106111 -apple/DCLM-7B_bfloat16_c85bfa168f999ce27e954808bc005a2748fda5c5_False,apple/DCLM-7B,c85bfa168f999ce27e954808bc005a2748fda5c5,bfloat16,pretrained,Original,OpenLMModel,13.9869771215513,FALSE,IFEval,0.217272392806642,21.7272392806642,BBH,0.423214236681842,19.7609349747722,MATH Level 5,0.0294561933534743,2.94561933534743,GPQA,0.315436241610738,8.7248322147651,MUSR,0.392072916666667,7.30911458333333,MMLU-PRO,0.31108710106383,23.4541223404255,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-11,2024-08-16,0,apple/DCLM-7B,apple-ascl,826,7,0.629955551509212 -arcee-ai/Arcee-Nova_bfloat16_ec3bfe88b83f81481daa04b6789c1e0d32827dc5_True,arcee-ai/Arcee-Nova,ec3bfe88b83f81481daa04b6789c1e0d32827dc5,bfloat16,chatmodels,Original,Qwen2ForCausalLM,43.9023352264525,TRUE,IFEval,0.790748547188128,79.0748547188128,BBH,0.694196965855899,56.7409875395207,MATH Level 5,0.429003021148036,42.9003021148036,GPQA,0.38506711409396,18.0089485458613,MUSR,0.456166666666667,17.2208333333333,MMLU-PRO,0.545212765957447,49.468085106383,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-16,2024-09-19,0,arcee-ai/Arcee-Nova,other,45,72.706,11.4932935647508 +apple/DCLM-7B_bfloat16_c85bfa168f999ce27e954808bc005a2748fda5c5_False,apple/DCLM-7B,c85bfa168f999ce27e954808bc005a2748fda5c5,bfloat16,pretrained,Original,OpenLMModel,13.9869771215513,FALSE,IFEval,0.217272392806642,21.7272392806642,BBH,0.423214236681842,19.7609349747722,MATH Level 5,0.0294561933534743,2.94561933534743,GPQA,0.315436241610738,8.7248322147651,MUSR,0.392072916666667,7.30911458333333,MMLU-PRO,0.31108710106383,23.4541223404255,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-11,2024-08-16,0,apple/DCLM-7B,apple-ascl,827,7,0.629955551509212 +arcee-ai/Arcee-Nova_bfloat16_ec3bfe88b83f81481daa04b6789c1e0d32827dc5_True,arcee-ai/Arcee-Nova,ec3bfe88b83f81481daa04b6789c1e0d32827dc5,bfloat16,chatmodels,Original,Qwen2ForCausalLM,43.9023352264525,TRUE,IFEval,0.790748547188128,79.0748547188128,BBH,0.694196965855899,56.7409875395207,MATH Level 5,0.429003021148036,42.9003021148036,GPQA,0.38506711409396,18.0089485458613,MUSR,0.456166666666667,17.2208333333333,MMLU-PRO,0.545212765957447,49.468085106383,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-16,2024-09-19,0,arcee-ai/Arcee-Nova,other,46,72.706,11.4932935647508 arcee-ai/Arcee-Spark_bfloat16_3fe368ea5fd32bc4a8d1bcf42510416f7fa28668_True,arcee-ai/Arcee-Spark,3fe368ea5fd32bc4a8d1bcf42510416f7fa28668,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,25.5364556314038,TRUE,IFEval,0.562087483432847,56.2087483432847,BBH,0.548947419856745,37.1385224558447,MATH Level 5,0.123111782477341,12.3111782477341,GPQA,0.307046979865772,7.60626398210291,MUSR,0.40209375,8.59505208333333,MMLU-PRO,0.382230718085106,31.3589686761229,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-22,2024-06-26,0,arcee-ai/Arcee-Spark,apache-2.0,86,7.616,1.09853282777225 arcee-ai/Arcee-Spark_float16_3fe368ea5fd32bc4a8d1bcf42510416f7fa28668_True,arcee-ai/Arcee-Spark,3fe368ea5fd32bc4a8d1bcf42510416f7fa28668,float16,chatmodels,Original,Qwen2ForCausalLM,25.4431687473776,TRUE,IFEval,0.571829412625168,57.1829412625168,BBH,0.548086411471413,36.9243904358649,MATH Level 5,0.11404833836858,11.404833836858,GPQA,0.306208053691275,7.49440715883669,MUSR,0.400760416666667,8.39505208333334,MMLU-PRO,0.381316489361702,31.2573877068558,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-22,2024-06-26,0,arcee-ai/Arcee-Spark,apache-2.0,86,7.616,1.13604019364973 arcee-ai/Llama-3.1-SuperNova-Lite_bfloat16_76246ca4448c1a11787daee0958b60ab27f17774_True,arcee-ai/Llama-3.1-SuperNova-Lite,76246ca4448c1a11787daee0958b60ab27f17774,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,30.0424065786489,TRUE,IFEval,0.801739384832245,80.1739384832245,BBH,0.515199211510482,31.5723402129807,MATH Level 5,0.173716012084592,17.3716012084592,GPQA,0.306208053691275,7.49440715883669,MUSR,0.416322916666667,11.6736979166667,MMLU-PRO,0.387716090425532,31.9684544917258,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-10,2024-09-17,2,meta-llama/Meta-Llama-3.1-8B,llama3,178,8.03,0.855993385011881 arcee-ai/Llama-Spark_bfloat16_6d74a617fbb17a1ada08528f2673c89f84fb062e_True,arcee-ai/Llama-Spark,6d74a617fbb17a1ada08528f2673c89f84fb062e,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,24.9224332761527,TRUE,IFEval,0.791073241222179,79.1073241222179,BBH,0.505350414574998,29.7702537002086,MATH Level 5,0.0120845921450151,1.20845921450151,GPQA,0.299496644295302,6.59955257270694,MUSR,0.359333333333333,2.61666666666667,MMLU-PRO,0.372091090425532,30.2323433806147,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-26,2024-08-08,0,arcee-ai/Llama-Spark,llama3,26,8.03,0.830714101745732 arcee-ai/SuperNova-Medius_bfloat16_e34fafcac2801be1ae5c7eb744e191a08119f2af_True,arcee-ai/SuperNova-Medius,e34fafcac2801be1ae5c7eb744e191a08119f2af,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,33.8924710529695,TRUE,IFEval,0.718358400156031,71.8358400156031,BBH,0.637728446311571,48.0050146271633,MATH Level 5,0.153323262839879,15.3323262839879,GPQA,0.333053691275168,11.0738255033557,MUSR,0.423270833333333,12.2755208333333,MMLU-PRO,0.503490691489362,44.8322990543735,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-02,2024-10-22,1,arcee-ai/SuperNova-Medius (Merge),apache-2.0,195,14.77,5.86781166745177 -arcee-ai/Virtuoso-Small_bfloat16_ca5dec1c6351ba6f2f0c59e609b94628a29c1459_True,arcee-ai/Virtuoso-Small,ca5dec1c6351ba6f2f0c59e609b94628a29c1459,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,39.4283232965703,TRUE,IFEval,0.793521190441362,79.3521190441362,BBH,0.651763312945478,50.3998463118999,MATH Level 5,0.342900302114804,34.2900302114804,GPQA,0.336409395973154,11.5212527964206,MUSR,0.43390625,14.43828125,MMLU-PRO,0.519115691489362,46.5684101654846,TRUE,FALSE,FALSE,FALSE,FALSE,2024-12-01,2024-12-03,1,arcee-ai/Virtuoso-Small (Merge),apache-2.0,36,14.77,1.51431412160642 +arcee-ai/Virtuoso-Small_bfloat16_ca5dec1c6351ba6f2f0c59e609b94628a29c1459_True,arcee-ai/Virtuoso-Small,ca5dec1c6351ba6f2f0c59e609b94628a29c1459,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,39.4283232965703,TRUE,IFEval,0.793521190441362,79.3521190441362,BBH,0.651763312945478,50.3998463118999,MATH Level 5,0.342900302114804,34.2900302114804,GPQA,0.336409395973154,11.5212527964206,MUSR,0.43390625,14.43828125,MMLU-PRO,0.519115691489362,46.5684101654846,TRUE,FALSE,FALSE,FALSE,FALSE,2024-12-01,2024-12-03,1,arcee-ai/Virtuoso-Small (Merge),apache-2.0,37,14.77,1.51431412160642 arcee-ai/raspberry-3B_bfloat16_66bf1346c060bbfe1f1b98cd22e7a26ada69cf70_True,arcee-ai/raspberry-3B,66bf1346c060bbfe1f1b98cd22e7a26ada69cf70,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,15.5380031214432,TRUE,IFEval,0.315416428409952,31.5416428409952,BBH,0.42689280188827,19.5282344009925,MATH Level 5,0.0845921450151058,8.45921450151058,GPQA,0.277684563758389,3.69127516778523,MUSR,0.412322916666667,9.40703125,MMLU-PRO,0.285405585106383,20.6006205673759,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-05,2024-10-07,1,Qwen/Qwen2.5-3B,other,36,3.086,1.03652651773508 argilla/notus-7b-v1_bfloat16_30172203a2d41cb487bf7e2b92a821080783b2c9_True,argilla/notus-7b-v1,30172203a2d41cb487bf7e2b92a821080783b2c9,bfloat16,chatmodels,Original,MistralForCausalLM,18.4113211888546,TRUE,IFEval,0.508207112683236,50.8207112683236,BBH,0.45118574073815,22.7471119611614,MATH Level 5,0.0279456193353474,2.79456193353474,GPQA,0.289429530201342,5.2572706935123,MUSR,0.336416666666667,6.58541666666667,MMLU-PRO,0.300365691489362,22.2628546099291,TRUE,FALSE,FALSE,FALSE,TRUE,2023-11-16,2024-06-27,2,mistralai/Mistral-7B-v0.1,mit,122,7.242,0.667908131155709 argilla/notux-8x7b-v1_bfloat16_0b29f9afcbae2ab4c5085638d8f5a7f6d44c6b17_True,argilla/notux-8x7b-v1,0b29f9afcbae2ab4c5085638d8f5a7f6d44c6b17,bfloat16,chatmodels,Original,MixtralForCausalLM,24.4282310956467,TRUE,IFEval,0.542229063329743,54.2229063329743,BBH,0.536330416451635,34.7580616829018,MATH Level 5,0.0966767371601208,9.66767371601208,GPQA,0.308724832214765,7.82997762863535,MUSR,0.41759375,10.5325520833333,MMLU-PRO,0.366023936170213,29.5582151300237,TRUE,FALSE,TRUE,FALSE,TRUE,2023-12-12,2024-06-12,2,mistralai/Mixtral-8x7B-v0.1,apache-2.0,165,46.703,21.3908445719779 @@ -1188,7 +1188,7 @@ cognitivecomputations/dolphin-2.9.1-yi-1.5-9b_bfloat16_91f0a521e3e2a0675a3549aa5 cognitivecomputations/dolphin-2.9.2-Phi-3-Medium_bfloat16_0470c5b912b51fa6e27d87a8ea7feafacd8cb101_True,cognitivecomputations/dolphin-2.9.2-Phi-3-Medium,0470c5b912b51fa6e27d87a8ea7feafacd8cb101,bfloat16,chatmodels,Original,MistralForCausalLM,25.6688971532864,TRUE,IFEval,0.424776260322611,42.4776260322611,BBH,0.645673930268653,49.721940305081,MATH Level 5,0.00604229607250755,0.604229607250755,GPQA,0.327181208053691,10.2908277404922,MUSR,0.419052083333333,11.41484375,MMLU-PRO,0.455535239361702,39.5039154846336,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-31,2024-08-05,1,cognitivecomputations/dolphin-2.9.2-Phi-3-Medium (Merge),mit,18,-1,0.84048179268982 cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated_float16_d50be5f22ca9745a2a3175996611d6a840318b7f_False,cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated,d50be5f22ca9745a2a3175996611d6a840318b7f,float16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,25.5900637203488,FALSE,IFEval,0.3612536957495,36.12536957495,BBH,0.612322545411745,45.4412665509377,MATH Level 5,0.123867069486405,12.3867069486405,GPQA,0.328020134228188,10.4026845637584,MUSR,0.411177083333333,10.3638020833333,MMLU-PRO,0.449384973404255,38.8205526004728,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-03,2024-06-27,1,cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated (Merge),mit,16,13.96,0.843953656499193 cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated_bfloat16_d50be5f22ca9745a2a3175996611d6a840318b7f_True,cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated,d50be5f22ca9745a2a3175996611d6a840318b7f,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,25.6184291763939,TRUE,IFEval,0.412361423245877,41.2361423245877,BBH,0.638289226729353,48.3853469127074,MATH Level 5,0.006797583081571,0.6797583081571,GPQA,0.328859060402685,10.5145413870246,MUSR,0.434927083333333,13.7325520833333,MMLU-PRO,0.452460106382979,39.1622340425532,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-03,2024-08-05,1,cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated (Merge),mit,16,13.96,0.820796596618691 -cognitivecomputations/dolphin-2.9.2-qwen2-72b_bfloat16_e79582577c2bf2af304221af0e8308b7e7d46ca1_True,cognitivecomputations/dolphin-2.9.2-qwen2-72b,e79582577c2bf2af304221af0e8308b7e7d46ca1,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,35.7452923179215,TRUE,IFEval,0.634377895096123,63.4377895096123,BBH,0.629636493958407,47.6961737282619,MATH Level 5,0.20619335347432,20.619335347432,GPQA,0.36996644295302,15.9955257270693,MUSR,0.452072916666667,17.0424479166667,MMLU-PRO,0.547124335106383,49.680481678487,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-27,2024-10-20,1,Qwen/Qwen2-72B,other,123,72,25.1155535276709 +cognitivecomputations/dolphin-2.9.2-qwen2-72b_bfloat16_e79582577c2bf2af304221af0e8308b7e7d46ca1_True,cognitivecomputations/dolphin-2.9.2-qwen2-72b,e79582577c2bf2af304221af0e8308b7e7d46ca1,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,35.7452923179215,TRUE,IFEval,0.634377895096123,63.4377895096123,BBH,0.629636493958407,47.6961737282619,MATH Level 5,0.20619335347432,20.619335347432,GPQA,0.36996644295302,15.9955257270693,MUSR,0.452072916666667,17.0424479166667,MMLU-PRO,0.547124335106383,49.680481678487,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-27,2024-10-20,1,Qwen/Qwen2-72B,other,124,72,25.1155535276709 cognitivecomputations/dolphin-2.9.2-qwen2-7b_bfloat16_c443c4eb5138ed746ac49ed98bf3c183dc5380ac_True,cognitivecomputations/dolphin-2.9.2-qwen2-7b,c443c4eb5138ed746ac49ed98bf3c183dc5380ac,bfloat16,chatmodels,Original,Qwen2ForCausalLM,21.1839653570505,TRUE,IFEval,0.353459930761491,35.3459930761491,BBH,0.489382637591956,27.9148749532555,MATH Level 5,0.129154078549849,12.9154078549849,GPQA,0.290268456375839,5.36912751677852,MUSR,0.419145833333333,11.6598958333333,MMLU-PRO,0.405086436170213,33.8984929078014,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-24,2024-07-10,1,Qwen/Qwen2-7B,apache-2.0,63,7.616,1.27919726982431 cognitivecomputations/dolphin-2.9.3-Yi-1.5-34B-32k_bfloat16_ff4eee6438194a670a95dff3118b5231eb568610_True,cognitivecomputations/dolphin-2.9.3-Yi-1.5-34B-32k,ff4eee6438194a670a95dff3118b5231eb568610,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,27.0732064143377,TRUE,IFEval,0.363926603633914,36.3926603633914,BBH,0.604699553777323,43.4064756523518,MATH Level 5,0.165407854984894,16.5407854984894,GPQA,0.343120805369128,12.4161073825503,MUSR,0.431052083333333,13.3481770833333,MMLU-PRO,0.463015292553192,40.3350325059102,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-23,2024-07-27,1,01-ai/Yi-1.5-34B-32k,apache-2.0,18,34,3.24526052711179 cognitivecomputations/dolphin-2.9.3-mistral-7B-32k_bfloat16_4f4273ee8e7930dd64e2c6121c79d12546b883e2_True,cognitivecomputations/dolphin-2.9.3-mistral-7B-32k,4f4273ee8e7930dd64e2c6121c79d12546b883e2,bfloat16,chatmodels,Original,MistralForCausalLM,19.3738721831618,TRUE,IFEval,0.412636249595518,41.2636249595518,BBH,0.48125401481062,26.9063538917805,MATH Level 5,0.0521148036253777,5.21148036253777,GPQA,0.285234899328859,4.6979865771812,MUSR,0.464260416666667,17.9325520833333,MMLU-PRO,0.282081117021277,20.2312352245863,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-25,2024-07-04,1,mistralai/Mistral-7B-v0.3,apache-2.0,46,7.248,0.600082580420255 @@ -1205,7 +1205,7 @@ cstr/llama3.1-8b-spaetzle-v90_bfloat16_717e5c3d31ed2465cd7cf927327adf677a9420b5_ cyberagent/calm3-22b-chat_bfloat16_055922aa0f0fb1fbfbc97a2e31134532485ee99b_True,cyberagent/calm3-22b-chat,055922aa0f0fb1fbfbc97a2e31134532485ee99b,bfloat16,chatmodels,Original,LlamaForCausalLM,21.3755896632195,TRUE,IFEval,0.509131327100981,50.9131327100981,BBH,0.499168324774605,29.5208839688583,MATH Level 5,0.0649546827794562,6.49546827794562,GPQA,0.276845637583893,3.57941834451902,MUSR,0.455322916666667,16.08203125,MMLU-PRO,0.294963430851064,21.662603427896,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-01,2024-07-04,0,cyberagent/calm3-22b-chat,apache-2.0,70,22.543,1.77424811813219 darkc0de/BuddyGlassNeverSleeps_float16_f8849498f02c94b68ef0308a7bf6637264949a7d_False,darkc0de/BuddyGlassNeverSleeps,f8849498f02c94b68ef0308a7bf6637264949a7d,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,19.8458178279584,FALSE,IFEval,0.423901913589276,42.3901913589276,BBH,0.497722816536468,28.4779534944187,MATH Level 5,0.0641993957703927,6.41993957703927,GPQA,0.294463087248322,5.92841163310962,MUSR,0.399270833333333,8.60885416666667,MMLU-PRO,0.345246010638298,27.2495567375887,FALSE,FALSE,FALSE,FALSE,FALSE,2024-09-16,2024-09-16,1,darkc0de/BuddyGlassNeverSleeps (Merge),"",2,8.03,1.35414877415844 darkc0de/BuddyGlass_v0.3_Xortron7MethedUpSwitchedUp_bfloat16_57367fefe01c7d9653c303b28449b416fc777d93_False,darkc0de/BuddyGlass_v0.3_Xortron7MethedUpSwitchedUp,57367fefe01c7d9653c303b28449b416fc777d93,bfloat16,basemergesandmoerges,Original,LlamaForCausalLM,22.2653148564924,FALSE,IFEval,0.435842453578727,43.5842453578727,BBH,0.524308799865672,31.869311081858,MATH Level 5,0.124622356495468,12.4622356495468,GPQA,0.298657718120805,6.48769574944072,MUSR,0.414333333333333,9.49166666666667,MMLU-PRO,0.367270611702128,29.6967346335697,FALSE,FALSE,FALSE,FALSE,FALSE,2024-09-10,2024-09-15,1,darkc0de/BuddyGlass_v0.3_Xortron7MethedUpSwitchedUp (Merge),"",1,0.007,0.898182046260927 -databricks/dbrx-instruct_bfloat16_c0a9245908c187da8f43a81e538e67ff360904ea_True,databricks/dbrx-instruct,c0a9245908c187da8f43a81e538e67ff360904ea,bfloat16,chatmodels,Original,DbrxForCausalLM,25.1990102724432,TRUE,IFEval,0.541579675261639,54.1579675261639,BBH,0.542896079693439,35.9638196035936,MATH Level 5,0.0687311178247734,6.87311178247734,GPQA,0.341442953020134,12.1923937360179,MUSR,0.426927083333333,12.19921875,MMLU-PRO,0.36826795212766,29.8075502364066,TRUE,FALSE,FALSE,FALSE,TRUE,2024-03-26,2024-06-12,0,databricks/dbrx-instruct,other,1104,131.597,47.95802727312 +databricks/dbrx-instruct_bfloat16_c0a9245908c187da8f43a81e538e67ff360904ea_True,databricks/dbrx-instruct,c0a9245908c187da8f43a81e538e67ff360904ea,bfloat16,chatmodels,Original,DbrxForCausalLM,25.1990102724432,TRUE,IFEval,0.541579675261639,54.1579675261639,BBH,0.542896079693439,35.9638196035936,MATH Level 5,0.0687311178247734,6.87311178247734,GPQA,0.341442953020134,12.1923937360179,MUSR,0.426927083333333,12.19921875,MMLU-PRO,0.36826795212766,29.8075502364066,TRUE,FALSE,FALSE,FALSE,TRUE,2024-03-26,2024-06-12,0,databricks/dbrx-instruct,other,1105,131.597,47.95802727312 databricks/dolly-v1-6b_bfloat16_c9a85b3a322b402e20c839c702c725afe0cb454d_False,databricks/dolly-v1-6b,c9a85b3a322b402e20c839c702c725afe0cb454d,bfloat16,pretrained,Original,GPTJForCausalLM,6.91829112647551,FALSE,IFEval,0.222443117594649,22.2443117594649,BBH,0.31720895287747,4.7813091701327,MATH Level 5,0.0151057401812689,1.51057401812689,GPQA,0.264261744966443,1.90156599552573,MUSR,0.400416666666667,8.11875,MMLU-PRO,0.126579122340426,2.95323581560284,TRUE,FALSE,FALSE,FALSE,TRUE,2023-03-23,2024-06-12,0,databricks/dolly-v1-6b,cc-by-nc-4.0,310,6,0.660779912276233 databricks/dolly-v2-12b_bfloat16_19308160448536e378e3db21a73a751579ee7fdd_False,databricks/dolly-v2-12b,19308160448536e378e3db21a73a751579ee7fdd,bfloat16,fine-tunedondomain-specificdatasets,Original,GPTNeoXForCausalLM,6.3830238203141,FALSE,IFEval,0.235507342739487,23.5507342739487,BBH,0.331997316737713,6.37789413745296,MATH Level 5,0.0143504531722054,1.43504531722054,GPQA,0.240771812080537,0,MUSR,0.37390625,5.50494791666667,MMLU-PRO,0.112865691489362,1.42952127659574,TRUE,FALSE,FALSE,FALSE,TRUE,2023-04-11,2024-06-12,0,databricks/dolly-v2-12b,mit,1950,12,1.39711946227966 databricks/dolly-v2-3b_bfloat16_f6c9be08f16fe4d3a719bee0a4a7c7415b5c65df_False,databricks/dolly-v2-3b,f6c9be08f16fe4d3a719bee0a4a7c7415b5c65df,bfloat16,fine-tunedondomain-specificdatasets,Original,GPTNeoXForCausalLM,5.46118895807585,FALSE,IFEval,0.224715975833012,22.4715975833012,BBH,0.307927859615448,3.32476895654539,MATH Level 5,0.006797583081571,0.6797583081571,GPQA,0.260906040268456,1.45413870246085,MUSR,0.33378125,3.22265625,MMLU-PRO,0.114527925531915,1.61421394799054,TRUE,FALSE,FALSE,FALSE,TRUE,2023-04-13,2024-06-12,0,databricks/dolly-v2-3b,mit,287,3,0.758084484077729 @@ -1224,7 +1224,7 @@ dfurman/Llama-3-8B-Orpo-v0.1_bfloat16_f02aef830e12a50892ac065826d5eb3dfc7675d1_T dfurman/Qwen2-72B-Orpo-v0.1_bfloat16_26c7bbaa728822c60bb47b2808972140653aae4c_True,dfurman/Qwen2-72B-Orpo-v0.1,26c7bbaa728822c60bb47b2808972140653aae4c,bfloat16,chatmodels,Original,Qwen2ForCausalLM,43.7694801124002,TRUE,IFEval,0.787975903934893,78.7975903934893,BBH,0.696902479054504,57.4143635101875,MATH Level 5,0.381419939577039,38.1419939577039,GPQA,0.384228187919463,17.8970917225951,MUSR,0.478427083333333,20.8700520833333,MMLU-PRO,0.54546210106383,49.4957890070922,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-05,2024-08-22,1,dfurman/Qwen2-72B-Orpo-v0.1 (Merge),other,4,72.699,12.6253316211726 dicta-il/dictalm2.0_bfloat16_f8ab3208e95a7b44a9a2fbb9bbbdd8ea11be509d_False,dicta-il/dictalm2.0,f8ab3208e95a7b44a9a2fbb9bbbdd8ea11be509d,bfloat16,continuouslypretrained,Original,MistralForCausalLM,11.8825972287699,FALSE,IFEval,0.241327455595597,24.1327455595597,BBH,0.401786911249591,16.489845615782,MATH Level 5,0.0173716012084592,1.73716012084592,GPQA,0.291946308724832,5.59284116331097,MUSR,0.38196875,5.51276041666667,MMLU-PRO,0.260472074468085,17.8302304964539,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-10,2024-07-31,0,dicta-il/dictalm2.0,apache-2.0,11,7.251,0.674038444369941 dicta-il/dictalm2.0-instruct_bfloat16_257c6023d6ac1bfa12110b7b17e7600da7da4e1e_True,dicta-il/dictalm2.0-instruct,257c6023d6ac1bfa12110b7b17e7600da7da4e1e,bfloat16,chatmodels,Original,MistralForCausalLM,16.5778116005355,TRUE,IFEval,0.441212649104376,44.1212649104376,BBH,0.425607849859129,19.6880758511942,MATH Level 5,0.0105740181268882,1.05740181268882,GPQA,0.302852348993289,7.04697986577182,MUSR,0.394583333333333,9.72291666666667,MMLU-PRO,0.260472074468085,17.8302304964539,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-14,2024-07-31,1,dicta-il/dictalm2.0,apache-2.0,18,7.251,0.648394803951855 -distilbert/distilgpt2_bfloat16_2290a62682d06624634c1f46a6ad5be0f47f38aa_False,distilbert/distilgpt2,2290a62682d06624634c1f46a6ad5be0f47f38aa,bfloat16,pretrained,Original,GPT2LMHeadModel,3.90156889267857,FALSE,IFEval,0.0611001032815153,6.11001032815153,BBH,0.303798814865054,2.83521984551396,MATH Level 5,0,0,GPQA,0.259228187919463,1.23042505592841,MUSR,0.420729166666667,11.1578125,MMLU-PRO,0.118683510638298,2.07594562647754,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-12,0,distilbert/distilgpt2,apache-2.0,454,0.088,0.123081540414122 +distilbert/distilgpt2_bfloat16_2290a62682d06624634c1f46a6ad5be0f47f38aa_False,distilbert/distilgpt2,2290a62682d06624634c1f46a6ad5be0f47f38aa,bfloat16,pretrained,Original,GPT2LMHeadModel,3.90156889267857,FALSE,IFEval,0.0611001032815153,6.11001032815153,BBH,0.303798814865054,2.83521984551396,MATH Level 5,0,0,GPQA,0.259228187919463,1.23042505592841,MUSR,0.420729166666667,11.1578125,MMLU-PRO,0.118683510638298,2.07594562647754,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-12,0,distilbert/distilgpt2,apache-2.0,455,0.088,0.123081540414122 divyanshukunwar/SASTRI_1_9B_float16_3afeb5b296b1d6489401105e2ea6fc5c00d09c07_True,divyanshukunwar/SASTRI_1_9B,3afeb5b296b1d6489401105e2ea6fc5c00d09c07,float16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,19.3839952752583,TRUE,IFEval,0.420729220689991,42.0729220689992,BBH,0.468049905111834,23.5342162567955,MATH Level 5,0.113293051359517,11.3293051359517,GPQA,0.321308724832215,9.50782997762864,MUSR,0.383114583333333,5.55598958333333,MMLU-PRO,0.318733377659575,24.3037086288416,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-20,2024-11-23,1,divyanshukunwar/SASTRI_1_9B (Merge),apache-2.0,0,5.211,3.89621542201034 djuna/G2-BigGSHT-27B-2_bfloat16_b52e0c08d19232acebf85b68ee5989cc23c0d519_True,djuna/G2-BigGSHT-27B-2,b52e0c08d19232acebf85b68ee5989cc23c0d519,bfloat16,basemergesandmoerges,Original,Gemma2ForCausalLM,32.1321485796558,TRUE,IFEval,0.797443006777572,79.7443006777573,BBH,0.641474454273013,48.8143720824057,MATH Level 5,0,0,GPQA,0.363255033557047,15.1006711409396,MUSR,0.407208333333333,9.934375,MMLU-PRO,0.452792553191489,39.1991725768322,FALSE,FALSE,FALSE,FALSE,FALSE,2024-10-29,2024-11-06,1,djuna/G2-BigGSHT-27B-2 (Merge),"",0,27.227,5.02542897503711 djuna/G2-GSHT_bfloat16_afa34f893a74af2a21b71f83d7bcc16aa818d157_True,djuna/G2-GSHT,afa34f893a74af2a21b71f83d7bcc16aa818d157,bfloat16,basemergesandmoerges,Original,Gemma2ForCausalLM,22.001317169113,TRUE,IFEval,0.563011697850592,56.3011697850592,BBH,0.526973049127021,30.9920590151257,MATH Level 5,0.0347432024169184,3.47432024169184,GPQA,0.325503355704698,10.0671140939597,MUSR,0.400572916666667,8.17161458333333,MMLU-PRO,0.307014627659575,23.0016252955083,FALSE,FALSE,FALSE,FALSE,FALSE,2024-09-09,2024-10-05,1,djuna/G2-GSHT (Merge),"",0,10.159,2.15169197000275 @@ -1321,7 +1321,7 @@ gmonsoon/gemma2-9b-sahabatai-v1-instruct-BaseTIES_bfloat16_43296081051afe5d7a426 google/codegemma-1.1-2b_bfloat16_9d69e500da236427eab5867552ffc87108964f4d_False,google/codegemma-1.1-2b,9d69e500da236427eab5867552ffc87108964f4d,bfloat16,pretrained,Original,GemmaForCausalLM,7.03316296850576,FALSE,IFEval,0.229362535849324,22.9362535849324,BBH,0.335341779024845,7.55122528000415,MATH Level 5,0.006797583081571,0.6797583081571,GPQA,0.26510067114094,2.01342281879195,MUSR,0.387145833333333,5.9265625,MMLU-PRO,0.12782579787234,3.09175531914893,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-30,2024-08-12,0,google/codegemma-1.1-2b,gemma,17,2.506,0.949883196052667 google/flan-t5-base_float16_7bcac572ce56db69c1ea7c8af255c5d7c9672fc2_False,google/flan-t5-base,7bcac572ce56db69c1ea7c8af255c5d7c9672fc2,float16,pretrained,Original,T5ForConditionalGeneration,6.23940848953395,FALSE,IFEval,0.189070555016246,18.9070555016246,BBH,0.352598059930032,11.3376936773049,MATH Level 5,0,0,GPQA,0.238255033557047,0,MUSR,0.367114583333333,3.22265625,MMLU-PRO,0.135721409574468,3.96904550827423,TRUE,FALSE,FALSE,FALSE,TRUE,2022-10-21,2024-08-14,0,google/flan-t5-base,apache-2.0,818,0.248,0.156621440424456 google/flan-t5-large_float16_0613663d0d48ea86ba8cb3d7a44f0f65dc596a2a_False,google/flan-t5-large,0613663d0d48ea86ba8cb3d7a44f0f65dc596a2a,float16,pretrained,Original,T5ForConditionalGeneration,9.41894870600608,FALSE,IFEval,0.220094903744287,22.0094903744287,BBH,0.415311503567943,17.5100182800673,MATH Level 5,0,0,GPQA,0.250838926174497,0.111856823266221,MUSR,0.408322916666667,9.00703125,MMLU-PRO,0.170877659574468,7.87529550827423,TRUE,FALSE,FALSE,FALSE,TRUE,2022-10-21,2024-08-14,0,google/flan-t5-large,apache-2.0,637,0.783,0.233491371635308 -google/flan-t5-small_float16_0fc9ddf78a1e988dac52e2dac162b0ede4fd74ab_False,google/flan-t5-small,0fc9ddf78a1e988dac52e2dac162b0ede4fd74ab,float16,pretrained,Original,T5ForConditionalGeneration,6.00378064236063,FALSE,IFEval,0.152425564169736,15.2425564169736,BBH,0.328290109764084,6.36311196167965,MATH Level 5,0,0,GPQA,0.260906040268456,1.45413870246085,MUSR,0.412291666666667,10.3697916666667,MMLU-PRO,0.123337765957447,2.59308510638298,TRUE,FALSE,FALSE,FALSE,TRUE,2022-10-21,2024-06-27,0,google/flan-t5-small,apache-2.0,285,0.077,0.143130242275139 +google/flan-t5-small_float16_0fc9ddf78a1e988dac52e2dac162b0ede4fd74ab_False,google/flan-t5-small,0fc9ddf78a1e988dac52e2dac162b0ede4fd74ab,float16,pretrained,Original,T5ForConditionalGeneration,6.00378064236063,FALSE,IFEval,0.152425564169736,15.2425564169736,BBH,0.328290109764084,6.36311196167965,MATH Level 5,0,0,GPQA,0.260906040268456,1.45413870246085,MUSR,0.412291666666667,10.3697916666667,MMLU-PRO,0.123337765957447,2.59308510638298,TRUE,FALSE,FALSE,FALSE,TRUE,2022-10-21,2024-06-27,0,google/flan-t5-small,apache-2.0,286,0.077,0.143130242275139 google/flan-t5-xl_float16_7d6315df2c2fb742f0f5b556879d730926ca9001_False,google/flan-t5-xl,7d6315df2c2fb742f0f5b556879d730926ca9001,float16,pretrained,Original,T5ForConditionalGeneration,11.5917795285333,FALSE,IFEval,0.223741893730856,22.3741893730856,BBH,0.453106360621123,22.6950558112154,MATH Level 5,0.000755287009063444,0.0755287009063444,GPQA,0.25251677852349,0.335570469798655,MUSR,0.41809375,11.3283854166667,MMLU-PRO,0.214677526595745,12.7419473995272,TRUE,FALSE,FALSE,FALSE,TRUE,2022-10-21,2024-08-07,0,google/flan-t5-xl,apache-2.0,473,2.85,0.348929344293381 google/flan-t5-xl_bfloat16_7d6315df2c2fb742f0f5b556879d730926ca9001_False,google/flan-t5-xl,7d6315df2c2fb742f0f5b556879d730926ca9001,bfloat16,pretrained,Original,T5ForConditionalGeneration,11.5871674375561,FALSE,IFEval,0.22069442412798,22.069442412798,BBH,0.45372172155694,22.8375876635233,MATH Level 5,0.000755287009063444,0.0755287009063444,GPQA,0.245805369127517,0,MUSR,0.42203125,11.85390625,MMLU-PRO,0.214178856382979,12.6865395981087,TRUE,FALSE,FALSE,FALSE,TRUE,2022-10-21,2024-08-07,0,google/flan-t5-xl,apache-2.0,473,2.85,0.285351730178784 google/flan-t5-xxl_float16_ae7c9136adc7555eeccc78cdd960dfd60fb346ce_False,google/flan-t5-xxl,ae7c9136adc7555eeccc78cdd960dfd60fb346ce,float16,fine-tunedondomain-specificdatasets,Original,T5ForConditionalGeneration,13.4858434255225,FALSE,IFEval,0.220045036059877,22.0045036059877,BBH,0.506588801577692,30.1192556001059,MATH Level 5,0,0,GPQA,0.27013422818792,2.68456375838927,MUSR,0.42175,11.1854166666667,MMLU-PRO,0.234291888297872,14.9213209219858,TRUE,FALSE,FALSE,FALSE,TRUE,2022-10-21,2024-09-06,0,google/flan-t5-xxl,apache-2.0,1212,11.267,0.70647682731463 @@ -1332,15 +1332,15 @@ google/gemma-2-27b_bfloat16_938270f5272feb02779b55c2bb2fffdd0f53ff0c_False,googl google/gemma-2-27b-it_bfloat16_f6c533e5eb013c7e31fc74ef042ac4f3fb5cf40b_True,google/gemma-2-27b-it,f6c533e5eb013c7e31fc74ef042ac4f3fb5cf40b,bfloat16,chatmodels,Original,Gemma2ForCausalLM,32.3223187688799,TRUE,IFEval,0.797767700811624,79.7767700811624,BBH,0.64513874331688,49.2728421513039,MATH Level 5,0.00755287009063444,0.755287009063444,GPQA,0.375,16.6666666666667,MUSR,0.403302083333333,9.11276041666667,MMLU-PRO,0.445146276595745,38.3495862884161,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-24,2024-08-07,1,google/gemma-2-27b,gemma,463,27.227,4.82621118669274 google/gemma-2-2b_bfloat16_4d05c88d00441bf62bf87dcfd29e204c05089f36_True,google/gemma-2-2b,4d05c88d00441bf62bf87dcfd29e204c05089f36,bfloat16,pretrained,Original,InternLM2ForCausalLM,10.1294631550552,TRUE,IFEval,0.199312269223438,19.9312269223438,BBH,0.365596699642259,11.7558075322361,MATH Level 5,0.0287009063444109,2.87009063444109,GPQA,0.26258389261745,1.67785234899329,MUSR,0.423177083333333,11.43046875,MMLU-PRO,0.218001994680851,13.1113327423168,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-16,2024-07-31,0,google/gemma-2-2b,gemma,454,2.614,1.51879572271398 google/gemma-2-2b_float16_0738188b3055bc98daf0fe7211f0091357e5b979_False,google/gemma-2-2b,0738188b3055bc98daf0fe7211f0091357e5b979,float16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,10.3344393348315,FALSE,IFEval,0.201760218442621,20.1760218442621,BBH,0.370867461247026,12.4973062285736,MATH Level 5,0.0287009063444109,2.87009063444109,GPQA,0.26258389261745,1.67785234899329,MUSR,0.421875,11.2677083333333,MMLU-PRO,0.221658909574468,13.5176566193853,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-16,2024-08-04,0,google/gemma-2-2b,gemma,454,2.614,1.41825735113158 -google/gemma-2-2b-it_bfloat16_2b6ac3ff954ad896c115bbfa1b571cd93ea2c20f_True,google/gemma-2-2b-it,2b6ac3ff954ad896c115bbfa1b571cd93ea2c20f,bfloat16,fine-tunedondomain-specificdatasets,Original,InternLM2ForCausalLM,17.0469392949665,TRUE,IFEval,0.566833778817981,56.6833778817981,BBH,0.419923089142747,17.9807928815234,MATH Level 5,0.000755287009063444,0.0755287009063444,GPQA,0.274328859060403,3.24384787472036,MUSR,0.392885416666667,7.07734375,MMLU-PRO,0.25498670212766,17.2207446808511,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-16,2024-07-31,1,google/gemma-2-2b,gemma,769,2.614,1.23474327420585 +google/gemma-2-2b-it_bfloat16_2b6ac3ff954ad896c115bbfa1b571cd93ea2c20f_True,google/gemma-2-2b-it,2b6ac3ff954ad896c115bbfa1b571cd93ea2c20f,bfloat16,fine-tunedondomain-specificdatasets,Original,InternLM2ForCausalLM,17.0469392949665,TRUE,IFEval,0.566833778817981,56.6833778817981,BBH,0.419923089142747,17.9807928815234,MATH Level 5,0.000755287009063444,0.0755287009063444,GPQA,0.274328859060403,3.24384787472036,MUSR,0.392885416666667,7.07734375,MMLU-PRO,0.25498670212766,17.2207446808511,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-16,2024-07-31,1,google/gemma-2-2b,gemma,771,2.614,1.23474327420585 google/gemma-2-2b-jpn-it_float16_6b046bbc091084a1ec89fe03e58871fde10868eb_False,google/gemma-2-2b-jpn-it,6b046bbc091084a1ec89fe03e58871fde10868eb,float16,pretrained,Original,Gemma2ForCausalLM,17.1154057059385,FALSE,IFEval,0.507782683280363,50.7782683280363,BBH,0.422556989006581,18.5256264498327,MATH Level 5,0.0347432024169184,3.47432024169184,GPQA,0.285234899328859,4.6979865771812,MUSR,0.396385416666667,7.68151041666667,MMLU-PRO,0.2578125,17.5347222222222,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-25,2024-10-11,2,google/gemma-2-2b,gemma,145,2.614,1.01143721051409 google/gemma-2-2b-jpn-it_bfloat16_6b046bbc091084a1ec89fe03e58871fde10868eb_True,google/gemma-2-2b-jpn-it,6b046bbc091084a1ec89fe03e58871fde10868eb,bfloat16,chatmodels,Original,Gemma2ForCausalLM,15.8855787074056,TRUE,IFEval,0.528840144150853,52.8840144150853,BBH,0.417844022621712,17.848086390818,MATH Level 5,0,0,GPQA,0.275167785234899,3.35570469798658,MUSR,0.372760416666667,4.92838541666667,MMLU-PRO,0.246675531914894,16.2972813238771,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-25,2024-10-14,2,google/gemma-2-2b,gemma,145,2.614,0.854400249040011 google/gemma-2-9b_bfloat16_beb0c08e9eeb0548f3aca2ac870792825c357b7d_False,google/gemma-2-9b,beb0c08e9eeb0548f3aca2ac870792825c357b7d,bfloat16,pretrained,Original,Gemma2ForCausalLM,21.1549343088298,FALSE,IFEval,0.203983208996574,20.3983208996574,BBH,0.537737339762188,34.0968185358978,MATH Level 5,0.131419939577039,13.1419939577039,GPQA,0.328859060402685,10.5145413870246,MUSR,0.446114583333333,14.29765625,MMLU-PRO,0.410322473404255,34.480274822695,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-24,2024-07-11,0,google/gemma-2-9b,gemma,608,9,5.6631856917904 -google/gemma-2-9b-it_bfloat16_1937c70277fcc5f7fb0fc772fc5bc69378996e71_True,google/gemma-2-9b-it,1937c70277fcc5f7fb0fc772fc5bc69378996e71,bfloat16,chatmodels,Original,Gemma2ForCausalLM,28.8627904641512,TRUE,IFEval,0.743562636027961,74.3562636027961,BBH,0.599034250416413,42.1366196836647,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.360738255033557,14.7651006711409,MUSR,0.407270833333333,9.7421875,MMLU-PRO,0.387549867021277,31.9499852245863,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-24,2024-07-11,1,google/gemma-2-9b,gemma,583,9,5.01449702077493 -google/gemma-2b_bfloat16_2ac59a5d7bf4e1425010f0d457dde7d146658953_False,google/gemma-2b,2ac59a5d7bf4e1425010f0d457dde7d146658953,bfloat16,pretrained,Original,GemmaForCausalLM,7.35870138352179,FALSE,IFEval,0.203758250331343,20.3758250331343,BBH,0.338099397582924,8.46671286484037,MATH Level 5,0.0302114803625378,3.02114803625378,GPQA,0.25503355704698,0.671140939597318,MUSR,0.39778125,7.55598958333334,MMLU-PRO,0.136552526595745,4.06139184397163,TRUE,FALSE,FALSE,FALSE,TRUE,2024-02-08,2024-06-12,0,google/gemma-2b,gemma,920,2.506,1.23625082450337 -google/gemma-2b-it_bfloat16_de144fb2268dee1066f515465df532c05e699d48_True,google/gemma-2b-it,de144fb2268dee1066f515465df532c05e699d48,bfloat16,chatmodels,Original,GemmaForCausalLM,7.22145367714292,TRUE,IFEval,0.269029508371122,26.9029508371122,BBH,0.315081919887885,5.21430302216362,MATH Level 5,0.00453172205438067,0.453172205438067,GPQA,0.278523489932886,3.80313199105145,MUSR,0.334125,3.03229166666667,MMLU-PRO,0.13530585106383,3.92287234042553,TRUE,FALSE,FALSE,FALSE,TRUE,2024-02-08,2024-06-12,0,google/gemma-2b-it,gemma,683,2.506,0.352950331047759 +google/gemma-2-9b-it_bfloat16_1937c70277fcc5f7fb0fc772fc5bc69378996e71_True,google/gemma-2-9b-it,1937c70277fcc5f7fb0fc772fc5bc69378996e71,bfloat16,chatmodels,Original,Gemma2ForCausalLM,28.8627904641512,TRUE,IFEval,0.743562636027961,74.3562636027961,BBH,0.599034250416413,42.1366196836647,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.360738255033557,14.7651006711409,MUSR,0.407270833333333,9.7421875,MMLU-PRO,0.387549867021277,31.9499852245863,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-24,2024-07-11,1,google/gemma-2-9b,gemma,585,9,5.01449702077493 +google/gemma-2b_bfloat16_2ac59a5d7bf4e1425010f0d457dde7d146658953_False,google/gemma-2b,2ac59a5d7bf4e1425010f0d457dde7d146658953,bfloat16,pretrained,Original,GemmaForCausalLM,7.35870138352179,FALSE,IFEval,0.203758250331343,20.3758250331343,BBH,0.338099397582924,8.46671286484037,MATH Level 5,0.0302114803625378,3.02114803625378,GPQA,0.25503355704698,0.671140939597318,MUSR,0.39778125,7.55598958333334,MMLU-PRO,0.136552526595745,4.06139184397163,TRUE,FALSE,FALSE,FALSE,TRUE,2024-02-08,2024-06-12,0,google/gemma-2b,gemma,922,2.506,1.23625082450337 +google/gemma-2b-it_bfloat16_de144fb2268dee1066f515465df532c05e699d48_True,google/gemma-2b-it,de144fb2268dee1066f515465df532c05e699d48,bfloat16,chatmodels,Original,GemmaForCausalLM,7.22145367714292,TRUE,IFEval,0.269029508371122,26.9029508371122,BBH,0.315081919887885,5.21430302216362,MATH Level 5,0.00453172205438067,0.453172205438067,GPQA,0.278523489932886,3.80313199105145,MUSR,0.334125,3.03229166666667,MMLU-PRO,0.13530585106383,3.92287234042553,TRUE,FALSE,FALSE,FALSE,TRUE,2024-02-08,2024-06-12,0,google/gemma-2b-it,gemma,684,2.506,0.352950331047759 google/gemma-7b_bfloat16_a0eac5b80dba224e6ed79d306df50b1e92c2125d_False,google/gemma-7b,a0eac5b80dba224e6ed79d306df50b1e92c2125d,bfloat16,pretrained,Original,GemmaForCausalLM,15.45540668709,FALSE,IFEval,0.265932171083835,26.5932171083835,BBH,0.436152852392864,21.1160993232917,MATH Level 5,0.074773413897281,7.4773413897281,GPQA,0.286912751677852,4.92170022371365,MUSR,0.406239583333333,10.9799479166667,MMLU-PRO,0.294797207446809,21.6441341607565,TRUE,FALSE,FALSE,FALSE,TRUE,2024-02-08,2024-06-08,0,google/gemma-7b,gemma,3075,8.538,1.25491405781993 -google/gemma-7b-it_bfloat16_18329f019fb74ca4b24f97371785268543d687d2_True,google/gemma-7b-it,18329f019fb74ca4b24f97371785268543d687d2,bfloat16,chatmodels,Original,GemmaForCausalLM,12.8681419014102,TRUE,IFEval,0.386832493339894,38.6832493339894,BBH,0.364558292227017,11.8800913445494,MATH Level 5,0.0181268882175227,1.81268882175227,GPQA,0.284395973154362,4.58612975391499,MUSR,0.427427083333333,12.5283854166667,MMLU-PRO,0.169464760638298,7.71830673758865,TRUE,FALSE,FALSE,FALSE,TRUE,2024-02-13,2024-06-12,1,google/gemma-7b,gemma,1139,8.538,1.0999544452693 +google/gemma-7b-it_bfloat16_18329f019fb74ca4b24f97371785268543d687d2_True,google/gemma-7b-it,18329f019fb74ca4b24f97371785268543d687d2,bfloat16,chatmodels,Original,GemmaForCausalLM,12.8681419014102,TRUE,IFEval,0.386832493339894,38.6832493339894,BBH,0.364558292227017,11.8800913445494,MATH Level 5,0.0181268882175227,1.81268882175227,GPQA,0.284395973154362,4.58612975391499,MUSR,0.427427083333333,12.5283854166667,MMLU-PRO,0.169464760638298,7.71830673758865,TRUE,FALSE,FALSE,FALSE,TRUE,2024-02-13,2024-06-12,1,google/gemma-7b,gemma,1140,8.538,1.0999544452693 google/mt5-base_float16_2eb15465c5dd7f72a8f7984306ad05ebc3dd1e1f_False,google/mt5-base,2eb15465c5dd7f72a8f7984306ad05ebc3dd1e1f,float16,fine-tunedondomain-specificdatasets,Original,MT5ForConditionalGeneration,3.56528212264935,FALSE,IFEval,0.164515707212419,16.4515707212419,BBH,0.288316002284888,1.29855138817669,MATH Level 5,0,0,GPQA,0.239093959731544,0,MUSR,0.367208333333333,2.86770833333333,MMLU-PRO,0.106964760638298,0.773862293144208,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-09-06,0,google/mt5-base,apache-2.0,197,0.39,0.200039818164465 google/mt5-small_float16_73fb5dbe4756edadc8fbe8c769b0a109493acf7a_False,google/mt5-small,73fb5dbe4756edadc8fbe8c769b0a109493acf7a,float16,fine-tunedondomain-specificdatasets,Original,MT5ForConditionalGeneration,4.25592817327735,FALSE,IFEval,0.171809687185557,17.1809687185557,BBH,0.276584202992908,1.07097147950089,MATH Level 5,0,0,GPQA,0.24244966442953,0,MUSR,0.38575,5.91875,MMLU-PRO,0.112283909574468,1.36487884160756,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-09-06,0,google/mt5-small,apache-2.0,115,0.17,0.180493674360773 google/mt5-xl_float16_63fc6450d80515b48e026b69ef2fbbd426433e84_False,google/mt5-xl,63fc6450d80515b48e026b69ef2fbbd426433e84,float16,fine-tunedondomain-specificdatasets,Original,MT5ForConditionalGeneration,5.19142015303163,FALSE,IFEval,0.195964485343333,19.5964485343333,BBH,0.304735837080435,3.2824619143354,MATH Level 5,0,0,GPQA,0.264261744966443,1.90156599552573,MUSR,0.379520833333333,5.04010416666667,MMLU-PRO,0.111951462765957,1.32794030732861,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-09-06,0,google/mt5-xl,apache-2.0,22,3.23,0.903767224577182 @@ -1349,11 +1349,11 @@ google/recurrentgemma-2b_bfloat16_195f13c55b371fc721eda0662c00c64642c70e17_False google/recurrentgemma-2b-it_bfloat16_150248167d171fbdf4b02e7d28a4b3d749e570f6_True,google/recurrentgemma-2b-it,150248167d171fbdf4b02e7d28a4b3d749e570f6,bfloat16,chatmodels,Original,RecurrentGemmaForCausalLM,7.9455529067766,TRUE,IFEval,0.294932999995567,29.4932999995567,BBH,0.333000472726066,7.97876384039156,MATH Level 5,0.0166163141993958,1.66163141993958,GPQA,0.253355704697987,0.447427293064876,MUSR,0.3340625,3.62447916666667,MMLU-PRO,0.140209441489362,4.46771572104019,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-08,2024-06-12,0,google/recurrentgemma-2b-it,gemma,109,2.683,1.9330359260412 google/recurrentgemma-9b_bfloat16_7b0ed98fb889ba8bdfa7c690f08f2e57a7c48dae_False,google/recurrentgemma-9b,7b0ed98fb889ba8bdfa7c690f08f2e57a7c48dae,bfloat16,pretrained,Original,RecurrentGemmaForCausalLM,13.6842846224724,FALSE,IFEval,0.311594347442564,31.1594347442564,BBH,0.395625686694284,15.3233688889974,MATH Level 5,0.0649546827794562,6.49546827794562,GPQA,0.285234899328859,4.6979865771812,MUSR,0.380260416666667,6.59921875,MMLU-PRO,0.260472074468085,17.8302304964539,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-07,2024-07-04,0,google/recurrentgemma-9b,gemma,59,9,23.2061900981738 google/recurrentgemma-9b-it_bfloat16_43e62f98c3d496a5469ef4b18c1b11e417d68d1d_True,google/recurrentgemma-9b-it,43e62f98c3d496a5469ef4b18c1b11e417d68d1d,bfloat16,chatmodels,Original,RecurrentGemmaForCausalLM,19.2307031231246,TRUE,IFEval,0.501038356006507,50.1038356006507,BBH,0.436718964902765,21.6215800847401,MATH Level 5,0.0672205438066465,6.72205438066465,GPQA,0.27013422818792,2.68456375838927,MUSR,0.43790625,13.7716145833333,MMLU-PRO,0.284325132978723,20.4805703309693,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-07,2024-07-05,0,google/recurrentgemma-9b-it,gemma,50,9,13.36260841274 -google/switch-base-8_float16_92fe2d22b024d9937146fe097ba3d3a7ba146e1b_False,google/switch-base-8,92fe2d22b024d9937146fe097ba3d3a7ba146e1b,float16,fine-tunedondomain-specificdatasets,Original,SwitchTransformersForConditionalGeneration,3.29595026839661,FALSE,IFEval,0.158520503375488,15.8520503375488,BBH,0.287631327306693,1.70247810498213,MATH Level 5,0,0,GPQA,0.25,0,MUSR,0.351739583333333,1.13333333333333,MMLU-PRO,0.109790558510638,1.08783983451537,TRUE,FALSE,FALSE,FALSE,TRUE,2022-10-24,2024-09-06,0,google/switch-base-8,apache-2.0,15,0.62,0.146702933877402 +google/switch-base-8_float16_92fe2d22b024d9937146fe097ba3d3a7ba146e1b_False,google/switch-base-8,92fe2d22b024d9937146fe097ba3d3a7ba146e1b,float16,fine-tunedondomain-specificdatasets,Original,SwitchTransformersForConditionalGeneration,3.29595026839661,FALSE,IFEval,0.158520503375488,15.8520503375488,BBH,0.287631327306693,1.70247810498213,MATH Level 5,0,0,GPQA,0.25,0,MUSR,0.351739583333333,1.13333333333333,MMLU-PRO,0.109790558510638,1.08783983451537,TRUE,FALSE,FALSE,FALSE,TRUE,2022-10-24,2024-09-06,0,google/switch-base-8,apache-2.0,16,0.62,0.146702933877402 google/umt5-base_float16_0de9394d54f8975e71838d309de1cb496c894ab9_False,google/umt5-base,0de9394d54f8975e71838d309de1cb496c894ab9,float16,fine-tunedondomain-specificdatasets,Original,UMT5ForConditionalGeneration,3.44104602550114,FALSE,IFEval,0.174632198123202,17.4632198123202,BBH,0.278772623289455,0.813553178847296,MATH Level 5,0,0,GPQA,0.254194630872483,0.559284116331097,MUSR,0.33821875,0.944010416666666,MMLU-PRO,0.107795877659574,0.866208628841606,TRUE,FALSE,FALSE,FALSE,TRUE,2023-07-02,2024-09-06,0,google/umt5-base,apache-2.0,13,-1,0.668046044558199 goulue5/merging_LLM_float16_587115b34d72ef957fee2d8348b3ade3ae06d4a8_False,goulue5/merging_LLM,587115b34d72ef957fee2d8348b3ade3ae06d4a8,float16,basemergesandmoerges,Original,Qwen2ForCausalLM,16.4099852745745,FALSE,IFEval,0.323260061082373,32.3260061082373,BBH,0.42164986115901,18.282830291312,MATH Level 5,0.0785498489425982,7.85498489425982,GPQA,0.291107382550336,5.48098434004475,MUSR,0.43328125,12.76015625,MMLU-PRO,0.29579454787234,21.7549497635934,FALSE,FALSE,FALSE,FALSE,FALSE,2024-11-21,2024-11-22,0,goulue5/merging_LLM,"",0,1.544,0.551465090928402 -gpt2_bfloat16_607a30d783dfa663caf39e06633721c8d4cfcd7e_False,gpt2,607a30d783dfa663caf39e06633721c8d4cfcd7e,bfloat16,pretrained,Original,GPT2LMHeadModel,6.39102973137443,FALSE,IFEval,0.193416800755329,19.3416800755329,BBH,0.303638540151673,2.71429784738774,MATH Level 5,0.00302114803625378,0.302114803625378,GPQA,0.26006711409396,1.34228187919463,MUSR,0.432416666666667,12.9854166666667,MMLU-PRO,0.114943484042553,1.66038711583924,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-26,0,gpt2,mit,2436,0.137,0.323928012416449 -gpt2_float16_607a30d783dfa663caf39e06633721c8d4cfcd7e_False,gpt2,607a30d783dfa663caf39e06633721c8d4cfcd7e,float16,pretrained,Original,GPT2LMHeadModel,5.97773692810457,FALSE,IFEval,0.0833333333333333,8.33333333333333,BBH,0.308333333333333,9.19975490196079,MATH Level 5,0,0,GPQA,0.233333333333333,0,MUSR,0.433333333333333,18.3333333333333,MMLU-PRO,0.1,0,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-26,0,gpt2,mit,2436,0.137,0.0392451730685468 +gpt2_bfloat16_607a30d783dfa663caf39e06633721c8d4cfcd7e_False,gpt2,607a30d783dfa663caf39e06633721c8d4cfcd7e,bfloat16,pretrained,Original,GPT2LMHeadModel,6.39102973137443,FALSE,IFEval,0.193416800755329,19.3416800755329,BBH,0.303638540151673,2.71429784738774,MATH Level 5,0.00302114803625378,0.302114803625378,GPQA,0.26006711409396,1.34228187919463,MUSR,0.432416666666667,12.9854166666667,MMLU-PRO,0.114943484042553,1.66038711583924,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-26,0,gpt2,mit,2442,0.137,0.323928012416449 +gpt2_float16_607a30d783dfa663caf39e06633721c8d4cfcd7e_False,gpt2,607a30d783dfa663caf39e06633721c8d4cfcd7e,float16,pretrained,Original,GPT2LMHeadModel,5.97773692810457,FALSE,IFEval,0.0833333333333333,8.33333333333333,BBH,0.308333333333333,9.19975490196079,MATH Level 5,0,0,GPQA,0.233333333333333,0,MUSR,0.433333333333333,18.3333333333333,MMLU-PRO,0.1,0,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-26,0,gpt2,mit,2442,0.137,0.0392451730685468 gradientai/Llama-3-8B-Instruct-Gradient-1048k_bfloat16_8697fb25cb77c852311e03b4464b8467471d56a4_True,gradientai/Llama-3-8B-Instruct-Gradient-1048k,8697fb25cb77c852311e03b4464b8467471d56a4,bfloat16,chatmodels,Original,LlamaForCausalLM,18.2455696265917,TRUE,IFEval,0.44555889484346,44.555889484346,BBH,0.434590310706957,21.0105289871587,MATH Level 5,0.0513595166163142,5.13595166163142,GPQA,0.277684563758389,3.69127516778523,MUSR,0.42975,13.51875,MMLU-PRO,0.29404920212766,21.5610224586288,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-29,2024-06-12,0,gradientai/Llama-3-8B-Instruct-Gradient-1048k,llama3,677,8.03,0.887164486766284 grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge_bfloat16_7a8d334dce0a2ce948f75612b8d3a61c53d094aa_False,grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge,7a8d334dce0a2ce948f75612b8d3a61c53d094aa,bfloat16,basemergesandmoerges,Original,LlamaForCausalLM,20.887036378959,FALSE,IFEval,0.427124474172972,42.7124474172972,BBH,0.496169453500683,28.2580149129877,MATH Level 5,0.102719033232628,10.2719033232628,GPQA,0.290268456375839,5.36912751677852,MUSR,0.404322916666667,9.54036458333333,MMLU-PRO,0.362533244680851,29.1703605200946,TRUE,TRUE,FALSE,FALSE,FALSE,2024-06-28,2024-06-29,1,grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge (Merge),llama3,2,8.03,0.54754835391993 grimjim/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge_bfloat16_8f4d460ea20e24e48914156af7def305c0cd347f_True,grimjim/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge,8f4d460ea20e24e48914156af7def305c0cd347f,bfloat16,basemergesandmoerges,Original,LlamaForCausalLM,23.6884747801112,TRUE,IFEval,0.680589724154133,68.0589724154133,BBH,0.502173409117659,29.0732859144765,MATH Level 5,0.06797583081571,6.797583081571,GPQA,0.26258389261745,1.67785234899329,MUSR,0.388510416666667,6.69713541666667,MMLU-PRO,0.368434175531915,29.8260195035461,TRUE,TRUE,FALSE,FALSE,FALSE,2024-06-28,2024-09-17,1,grimjim/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge (Merge),llama3,2,8,0.616941673112788 @@ -1431,7 +1431,7 @@ icefog72/IceSakeV6RP-7b_float16_6838e68d35d037b0ef9b04a9de1ebc8ab508cd45_False,i icefog72/IceSakeV8RP-7b_float16_0f8f73fe356583e561479c689aa6597435327f4e_True,icefog72/IceSakeV8RP-7b,0f8f73fe356583e561479c689aa6597435327f4e,float16,basemergesandmoerges,Original,MistralForCausalLM,21.7650153990159,TRUE,IFEval,0.608574138840499,60.8574138840499,BBH,0.488471413379602,28.9662582332666,MATH Level 5,0.0641993957703928,6.41993957703928,GPQA,0.276006711409396,3.4675615212528,MUSR,0.399270833333333,8.5421875,MMLU-PRO,0.301030585106383,22.336731678487,TRUE,TRUE,FALSE,FALSE,FALSE,2024-06-26,2024-06-26,0,icefog72/IceSakeV8RP-7b,cc-by-nc-4.0,1,7.242,0.648285409734146 icefog72/IceTea21EnergyDrinkRPV13-DPOv3_bfloat16_2d4b4fd596ff0f6706a5752198e59da6ffc08067_False,icefog72/IceTea21EnergyDrinkRPV13-DPOv3,2d4b4fd596ff0f6706a5752198e59da6ffc08067,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,21.6842587279325,FALSE,IFEval,0.52634232724726,52.634232724726,BBH,0.501958758423263,30.6127340167025,MATH Level 5,0.0589123867069487,5.89123867069487,GPQA,0.283557046979866,4.47427293064877,MUSR,0.4371875,13.6484375,MMLU-PRO,0.305601728723404,22.8446365248227,FALSE,FALSE,FALSE,FALSE,FALSE,2024-09-05,2024-09-06,1,icefog72/IceTea21EnergyDrinkRPV13-DPOv3 (Merge),"",2,7.242,0.57994204720106 icefog72/IceTea21EnergyDrinkRPV13-DPOv3.5_bfloat16_0b0b0864347c3fad2b4d3e102f2f9839d20e296c_False,icefog72/IceTea21EnergyDrinkRPV13-DPOv3.5,0b0b0864347c3fad2b4d3e102f2f9839d20e296c,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,17.3087994924629,FALSE,IFEval,0.487099784128335,48.7099784128335,BBH,0.439966001310903,22.5732257792367,MATH Level 5,0.0354984894259819,3.54984894259819,GPQA,0.284395973154362,4.58612975391499,MUSR,0.396416666666667,7.78541666666667,MMLU-PRO,0.249833776595745,16.6481973995272,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-09-25,0,Removed,"",0,7.242,0.500728699428476 -ifable/gemma-2-Ifable-9B_bfloat16_d3dbde4efb93ea0a4f247de82541479de6b03160_False,ifable/gemma-2-Ifable-9B,d3dbde4efb93ea0a4f247de82541479de6b03160,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,22.8886905557519,FALSE,IFEval,0.29842927875814,29.842927875814,BBH,0.586611555669324,41.0326446462653,MATH Level 5,0.0989425981873112,9.89425981873112,GPQA,0.341442953020134,12.1923937360179,MUSR,0.40525,8.52291666666667,MMLU-PRO,0.422623005319149,35.8470005910166,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-10,2024-09-25,0,ifable/gemma-2-Ifable-9B,gemma,37,9.242,4.31760442146203 +ifable/gemma-2-Ifable-9B_bfloat16_d3dbde4efb93ea0a4f247de82541479de6b03160_False,ifable/gemma-2-Ifable-9B,d3dbde4efb93ea0a4f247de82541479de6b03160,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,22.8886905557519,FALSE,IFEval,0.29842927875814,29.842927875814,BBH,0.586611555669324,41.0326446462653,MATH Level 5,0.0989425981873112,9.89425981873112,GPQA,0.341442953020134,12.1923937360179,MUSR,0.40525,8.52291666666667,MMLU-PRO,0.422623005319149,35.8470005910166,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-10,2024-09-25,0,ifable/gemma-2-Ifable-9B,gemma,38,9.242,4.31760442146203 informatiker/Qwen2-7B-Instruct-abliterated_bfloat16_7577d60acfe4544d5ab303f0a4d69a9fcb9cf1aa_True,informatiker/Qwen2-7B-Instruct-abliterated,7577d60acfe4544d5ab303f0a4d69a9fcb9cf1aa,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,25.1216036134891,TRUE,IFEval,0.582170862201182,58.2170862201182,BBH,0.553426551593674,37.7957234413659,MATH Level 5,0.0913897280966767,9.13897280966767,GPQA,0.301174496644295,6.82326621923937,MUSR,0.388791666666667,6.83229166666667,MMLU-PRO,0.387300531914894,31.9222813238771,FALSE,FALSE,FALSE,FALSE,FALSE,2024-07-10,2024-09-15,0,informatiker/Qwen2-7B-Instruct-abliterated,"",6,7.616,1.06060504568381 instruction-pretrain/InstructLM-500M_float16_e9d33823c76303dfaff6a8397a8b70d0118ea350_False,instruction-pretrain/InstructLM-500M,e9d33823c76303dfaff6a8397a8b70d0118ea350,float16,pretrained,Original,MistralForCausalLM,2.85435031976667,FALSE,IFEval,0.1027662158628,10.27662158628,BBH,0.294087178725297,2.31705371604848,MATH Level 5,0,0,GPQA,0.256711409395973,0.894854586129753,MUSR,0.352822916666667,2.06953125,MMLU-PRO,0.114112367021277,1.56804078014184,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-18,2024-06-27,0,instruction-pretrain/InstructLM-500M,apache-2.0,34,0.5,0.245792145066826 internlm/internlm2-1_8b_bfloat16_c24f301c7374ad9f9b58d1ea80f68b5f57cbca13_False,internlm/internlm2-1_8b,c24f301c7374ad9f9b58d1ea80f68b5f57cbca13,bfloat16,pretrained,Original,InternLM2ForCausalLM,8.59707245146007,FALSE,IFEval,0.219770209710236,21.9770209710236,BBH,0.38797328000281,13.6338579659067,MATH Level 5,0.0120845921450151,1.20845921450151,GPQA,0.248322147651007,0,MUSR,0.38128125,8.22682291666667,MMLU-PRO,0.158826462765957,6.53627364066194,TRUE,FALSE,FALSE,FALSE,TRUE,2024-01-30,2024-06-12,0,internlm/internlm2-1_8b,other,28,8,0.663645516912293 @@ -1500,7 +1500,7 @@ jpacifico/Chocolatine-3B-Instruct-DPO-v1.2_float16_ebc9de6c266586adb1ec0db31bf05 jsfs11/MixtureofMerges-MoE-4x7b-v4_bfloat16_2b98406f20a874184dbffb5ed24e1f4b5063ec4b_False,jsfs11/MixtureofMerges-MoE-4x7b-v4,2b98406f20a874184dbffb5ed24e1f4b5063ec4b,bfloat16,basemergesandmoerges,Original,MixtralForCausalLM,20.0475374475942,FALSE,IFEval,0.402994055772018,40.2994055772018,BBH,0.516900710378601,32.2179981953369,MATH Level 5,0.0649546827794562,6.49546827794562,GPQA,0.286073825503356,4.80984340044743,MUSR,0.438552083333333,13.8856770833333,MMLU-PRO,0.303191489361702,22.5768321513002,TRUE,TRUE,TRUE,FALSE,FALSE,2024-02-11,2024-08-05,1,jsfs11/MixtureofMerges-MoE-4x7b-v4 (Merge),apache-2.0,4,24.154,1.38382780654089 jsfs11/MixtureofMerges-MoE-4x7b-v5_bfloat16_c1b5ce7144b966062df7627d2482a59e0df3757c_False,jsfs11/MixtureofMerges-MoE-4x7b-v5,c1b5ce7144b966062df7627d2482a59e0df3757c,bfloat16,basemergesandmoerges,Original,MixtralForCausalLM,20.4475291893853,FALSE,IFEval,0.419930229568656,41.9930229568656,BBH,0.519848125708369,32.8267241806806,MATH Level 5,0.0762839879154079,7.62839879154079,GPQA,0.284395973154362,4.58612975391499,MUSR,0.430489583333333,12.34453125,MMLU-PRO,0.309757313829787,23.3063682033097,TRUE,TRUE,TRUE,FALSE,FALSE,2024-02-25,2024-08-05,1,jsfs11/MixtureofMerges-MoE-4x7b-v5 (Merge),apache-2.0,1,24.154,1.43127240349892 kaist-ai/janus-7b_bfloat16_f19c614ae7c81db06af1655d297c67afa99ad286_False,kaist-ai/janus-7b,f19c614ae7c81db06af1655d297c67afa99ad286,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,17.6547631381676,FALSE,IFEval,0.377514993550446,37.7514993550446,BBH,0.469366759154163,25.7498700210616,MATH Level 5,0.0430513595166163,4.30513595166163,GPQA,0.272651006711409,3.02013422818792,MUSR,0.440104166666667,14.2796875,MMLU-PRO,0.287400265957447,20.8222517730496,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-04,2024-10-09,1,alpindale/Mistral-7B-v0.2-hf,apache-2.0,8,7.242,0.606603498340744 -kaist-ai/janus-dpo-7b_bfloat16_a414396b6d03fba75d12ccf7d8391186b4b639ce_False,kaist-ai/janus-dpo-7b,a414396b6d03fba75d12ccf7d8391186b4b639ce,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,18.53164895276,FALSE,IFEval,0.400271280203194,40.0271280203194,BBH,0.477258110489498,27.0909015768144,MATH Level 5,0.0415407854984894,4.15407854984894,GPQA,0.281879194630873,4.25055928411633,MUSR,0.438739583333333,13.7091145833333,MMLU-PRO,0.297623005319149,21.9581117021277,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-25,2024-10-09,1,Removed,apache-2.0,2,7.242,0.626428353674646 +kaist-ai/janus-dpo-7b_bfloat16_a414396b6d03fba75d12ccf7d8391186b4b639ce_False,kaist-ai/janus-dpo-7b,a414396b6d03fba75d12ccf7d8391186b4b639ce,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,18.53164895276,FALSE,IFEval,0.400271280203194,40.0271280203194,BBH,0.477258110489498,27.0909015768144,MATH Level 5,0.0415407854984894,4.15407854984894,GPQA,0.281879194630873,4.25055928411633,MUSR,0.438739583333333,13.7091145833333,MMLU-PRO,0.297623005319149,21.9581117021277,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-25,2024-10-09,1,Removed,apache-2.0,3,7.242,0.626428353674646 kaist-ai/janus-rm-7b_bfloat16_ffdbcc353ad4034fdfa68a767d265920d5f3e71c_False,kaist-ai/janus-rm-7b,ffdbcc353ad4034fdfa68a767d265920d5f3e71c,bfloat16,fine-tunedondomain-specificdatasets,Original,LLMForSequenceRegression,4.7755988324969,FALSE,IFEval,0.177804891022487,17.7804891022487,BBH,0.305646744678814,3.27778120364708,MATH Level 5,0,0,GPQA,0.251677852348993,0.223713646532442,MUSR,0.388291666666667,5.96979166666667,MMLU-PRO,0.112616356382979,1.40181737588652,TRUE,FALSE,FALSE,FALSE,FALSE,2024-05-09,2024-10-09,0,kaist-ai/janus-rm-7b,apache-2.0,4,7.111,0.539110601018549 kaist-ai/mistral-orpo-capybara-7k_bfloat16_24c1172060658a1923c9b454796857e2cc59fbeb_True,kaist-ai/mistral-orpo-capybara-7k,24c1172060658a1923c9b454796857e2cc59fbeb,bfloat16,chatmodels,Original,MistralForCausalLM,19.1831302298799,TRUE,IFEval,0.536733644507684,53.6733644507684,BBH,0.448899518549217,23.4343591162769,MATH Level 5,0.0370090634441088,3.70090634441088,GPQA,0.286073825503356,4.80984340044743,MUSR,0.396354166666667,7.57760416666667,MMLU-PRO,0.297124335106383,21.9027039007092,TRUE,FALSE,FALSE,FALSE,FALSE,2024-03-23,2024-10-09,1,kaist-ai/mistral-orpo-capybara-7k (Merge),mit,26,7.242,0.66074353398375 keeeeenw/MicroLlama_float16_8d5874ca07b86ea1ea2e71eea96212278506ba65_False,keeeeenw/MicroLlama,8d5874ca07b86ea1ea2e71eea96212278506ba65,float16,pretrained,Original,LlamaForCausalLM,5.0772665895411,FALSE,IFEval,0.198537657858925,19.8537657858925,BBH,0.300731399134717,2.83136363636364,MATH Level 5,0,0,GPQA,0.260906040268456,1.45413870246085,MUSR,0.3698125,4.79322916666667,MMLU-PRO,0.113779920212766,1.53110224586288,TRUE,FALSE,FALSE,FALSE,FALSE,2024-03-29,2024-09-15,0,keeeeenw/MicroLlama,apache-2.0,39,0.305,0.185767889535007 @@ -1599,40 +1599,40 @@ meetkai/functionary-small-v3.1_bfloat16_8e43bc1d2e259b91799e704c410a95b8ca458121 meraGPT/mera-mix-4x7B_bfloat16_09d965c5ef9b66ce419986027e03a915cb869e43_True,meraGPT/mera-mix-4x7B,09d965c5ef9b66ce419986027e03a915cb869e43,bfloat16,basemergesandmoerges,Original,MixtralForCausalLM,17.8549587329397,TRUE,IFEval,0.483177967792125,48.3177967792125,BBH,0.401898991636617,17.486438954655,MATH Level 5,0.0536253776435045,5.36253776435045,GPQA,0.304530201342282,7.27069351230425,MUSR,0.40565625,9.27369791666667,MMLU-PRO,0.274767287234043,19.4185874704492,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-13,2024-06-27,0,meraGPT/mera-mix-4x7B,apache-2.0,18,24.154,1.66440066308799 meta-llama/Llama-2-13b-chat-hf_float16_a2cb7a712bb6e5e736ca7f8cd98167f81a0b5bd8_True,meta-llama/Llama-2-13b-chat-hf,a2cb7a712bb6e5e736ca7f8cd98167f81a0b5bd8,float16,chatmodels,Original,LlamaForCausalLM,11.0163422752105,TRUE,IFEval,0.398472719052115,39.8472719052115,BBH,0.334273670667142,7.15537996862699,MATH Level 5,0.006797583081571,0.6797583081571,GPQA,0.231543624161074,0,MUSR,0.400729166666667,8.1578125,MMLU-PRO,0.192320478723404,10.2578309692671,TRUE,FALSE,FALSE,FALSE,TRUE,2023-07-13,2024-06-12,0,meta-llama/Llama-2-13b-chat-hf,llama2,1034,13.016,0.874569508215166 meta-llama/Llama-2-13b-hf_float16_5c31dfb671ce7cfe2d7bb7c04375e44c55e815b1_False,meta-llama/Llama-2-13b-hf,5c31dfb671ce7cfe2d7bb7c04375e44c55e815b1,float16,pretrained,Original,LlamaForCausalLM,11.0148335140031,FALSE,IFEval,0.248246873850273,24.8246873850273,BBH,0.412562422338351,17.2225598250581,MATH Level 5,0.0120845921450151,1.20845921450151,GPQA,0.281040268456376,4.13870246085012,MUSR,0.35375,3.38541666666667,MMLU-PRO,0.237782579787234,15.3091755319149,TRUE,FALSE,FALSE,FALSE,TRUE,2023-07-13,2024-06-12,0,meta-llama/Llama-2-13b-hf,llama2,575,13.016,1.11238015630798 -meta-llama/Llama-2-70b-chat-hf_float16_e9149a12809580e8602995856f8098ce973d1080_True,meta-llama/Llama-2-70b-chat-hf,e9149a12809580e8602995856f8098ce973d1080,float16,chatmodels,Original,LlamaForCausalLM,12.7464047385667,TRUE,IFEval,0.495792275606502,49.5792275606502,BBH,0.304247414616427,4.61376708259061,MATH Level 5,0.00981873111782478,0.981873111782478,GPQA,0.264261744966443,1.90156599552573,MUSR,0.368666666666667,3.48333333333334,MMLU-PRO,0.24326795212766,15.9186613475177,TRUE,FALSE,FALSE,FALSE,TRUE,2023-07-14,2024-06-12,0,meta-llama/Llama-2-70b-chat-hf,llama2,2164,68.977,22.8984550552606 -meta-llama/Llama-2-70b-hf_float16_3aba440b59558f995867ba6e1f58f21d0336b5bb_False,meta-llama/Llama-2-70b-hf,3aba440b59558f995867ba6e1f58f21d0336b5bb,float16,pretrained,Original,LlamaForCausalLM,18.3096580216144,FALSE,IFEval,0.240678067527494,24.0678067527494,BBH,0.547259119044934,35.9000618637217,MATH Level 5,0.0287009063444109,2.87009063444109,GPQA,0.302852348993289,7.04697986577182,MUSR,0.412354166666667,9.77760416666667,MMLU-PRO,0.371758643617021,30.1954048463357,TRUE,FALSE,FALSE,FALSE,TRUE,2023-07-11,2024-06-12,0,meta-llama/Llama-2-70b-hf,llama2,838,68.977,29.6212466171519 -meta-llama/Llama-2-7b-chat-hf_float16_f5db02db724555f92da89c216ac04704f23d4590_True,meta-llama/Llama-2-7b-chat-hf,f5db02db724555f92da89c216ac04704f23d4590,float16,pretrained,Original,LlamaForCausalLM,9.39548527825095,TRUE,IFEval,0.398647810032935,39.8647810032935,BBH,0.311354635500219,4.45917164595948,MATH Level 5,0.006797583081571,0.6797583081571,GPQA,0.253355704697987,0.447427293064876,MUSR,0.367552083333333,3.27734375,MMLU-PRO,0.168799867021277,7.64442966903073,TRUE,FALSE,FALSE,FALSE,TRUE,2023-07-13,2024-08-30,0,meta-llama/Llama-2-7b-chat-hf,llama2,4058,6.738,1.15687903615516 -meta-llama/Llama-2-7b-hf_float16_01c7f73d771dfac7d292323805ebc428287df4f9_False,meta-llama/Llama-2-7b-hf,01c7f73d771dfac7d292323805ebc428287df4f9,float16,pretrained,Original,LlamaForCausalLM,8.73082889563367,FALSE,IFEval,0.251893863836842,25.1893863836842,BBH,0.349619581998218,10.351416657849,MATH Level 5,0.0128398791540786,1.28398791540786,GPQA,0.266778523489933,2.23713646532438,MUSR,0.3700625,3.7578125,MMLU-PRO,0.18608710106383,9.56523345153664,TRUE,FALSE,FALSE,FALSE,TRUE,2023-07-13,2024-06-12,0,meta-llama/Llama-2-7b-hf,llama2,1843,6.738,0.563094562772064 -meta-llama/Llama-3.1-8B_float16_d04e592bb4f6aa9cfee91e2e20afa771667e1d4b_False,meta-llama/Llama-3.1-8B,d04e592bb4f6aa9cfee91e2e20afa771667e1d4b,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,14.2194553235834,FALSE,IFEval,0.124598288097803,12.4598288097803,BBH,0.465959054460073,25.3044706347549,MATH Level 5,0.0536253776435045,5.36253776435045,GPQA,0.310402684563758,8.05369127516779,MUSR,0.3811875,8.71510416666667,MMLU-PRO,0.328789893617021,25.4210992907801,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-14,2024-12-07,0,meta-llama/Llama-3.1-8B,llama3.1,1191,8.03,0.713243580943846 -meta-llama/Llama-3.2-1B_bfloat16_a7c18587d7f473bfea02aa5639aa349403307b54_False,meta-llama/Llama-3.2-1B,a7c18587d7f473bfea02aa5639aa349403307b54,bfloat16,pretrained,Original,LlamaForCausalLM,4.03149449541509,FALSE,IFEval,0.147779004153424,14.7779004153424,BBH,0.311495409646081,4.36602965655676,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.228187919463087,0,MUSR,0.344729166666667,2.5578125,MMLU-PRO,0.120345744680851,2.26063829787234,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-18,2024-09-23,0,meta-llama/Llama-3.2-1B,llama3.2,1242,1.24,0.41912851784102 -meta-llama/Llama-3.2-1B-Instruct_bfloat16_d0a2081ed47e20ce524e8bc5d132f3fad2f69ff0_True,meta-llama/Llama-3.2-1B-Instruct,d0a2081ed47e20ce524e8bc5d132f3fad2f69ff0,bfloat16,chatmodels,Original,LlamaForCausalLM,13.8137204928249,TRUE,IFEval,0.569831380736446,56.9831380736446,BBH,0.349684980617683,8.74252131230305,MATH Level 5,0.0324773413897281,3.24773413897281,GPQA,0.275167785234899,3.35570469798658,MUSR,0.332854166666667,2.9734375,MMLU-PRO,0.168218085106383,7.57978723404255,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-18,2024-09-23,0,meta-llama/Llama-3.2-1B-Instruct,llama3.2,631,1.24,0.404904524907622 -meta-llama/Llama-3.2-3B_bfloat16_95c102307f55fbd6d18ddf28bfbcb537ffdc2806_False,meta-llama/Llama-3.2-3B,95c102307f55fbd6d18ddf28bfbcb537ffdc2806,bfloat16,pretrained,Original,LlamaForCausalLM,8.5845296652033,FALSE,IFEval,0.133740696906431,13.374069690643,BBH,0.390511711699106,14.2326648843641,MATH Level 5,0.0120845921450151,1.20845921450151,GPQA,0.26761744966443,2.3489932885906,MUSR,0.35771875,3.81484375,MMLU-PRO,0.248753324468085,16.5281471631206,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-18,2024-09-27,0,meta-llama/Llama-3.2-3B,llama3.2,398,3.213,1.33181264899492 -meta-llama/Llama-3.2-3B-Instruct_bfloat16_276b29ce8303c9b88966a9b32fc75692dce4d8e1_True,meta-llama/Llama-3.2-3B-Instruct,276b29ce8303c9b88966a9b32fc75692dce4d8e1,bfloat16,chatmodels,Original,LlamaForCausalLM,24.1165339900694,TRUE,IFEval,0.739316125657699,73.9316125657699,BBH,0.461007023946607,24.0591864468855,MATH Level 5,0.171450151057402,17.1450151057402,GPQA,0.278523489932886,3.80313199105145,MUSR,0.352854166666667,1.3734375,MMLU-PRO,0.319481382978723,24.3868203309693,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-18,2024-09-27,0,meta-llama/Llama-3.2-3B-Instruct,llama3.2,773,3.213,1.27120351986613 -meta-llama/Llama-3.3-70B-Instruct_bfloat16__False,meta-llama/Llama-3.3-70B-Instruct,"",bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,36.8288410384085,FALSE,IFEval,0.899758197139146,89.9758197139146,BBH,0.691931282832581,56.5614107880222,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.328859060402685,10.5145413870246,MUSR,0.446125,15.565625,MMLU-PRO,0.533161569148936,48.1290632387707,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-26,2024-12-09,1,meta-llama/Llama-3.3-70B-Instruct (Merge),llama3.3,937,70.554,38.2795370537265 -meta-llama/Meta-Llama-3-70B_bfloat16_b4d08b7db49d488da3ac49adf25a6b9ac01ae338_False,meta-llama/Meta-Llama-3-70B,b4d08b7db49d488da3ac49adf25a6b9ac01ae338,bfloat16,pretrained,Original,LlamaForCausalLM,26.6675858211602,FALSE,IFEval,0.160319064526567,16.0319064526567,BBH,0.646107459990447,48.7098126475059,MATH Level 5,0.183534743202417,18.3534743202417,GPQA,0.397651006711409,19.6868008948546,MUSR,0.451822916666667,16.0111979166667,MMLU-PRO,0.470910904255319,41.2123226950355,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-17,2024-06-12,0,meta-llama/Meta-Llama-3-70B,llama3,835,70.554,23.4071857793614 -meta-llama/Meta-Llama-3-70B-Instruct_bfloat16_7129260dd854a80eb10ace5f61c20324b472b31c_True,meta-llama/Meta-Llama-3-70B-Instruct,7129260dd854a80eb10ace5f61c20324b472b31c,bfloat16,chatmodels,Original,LlamaForCausalLM,36.5106934142651,TRUE,IFEval,0.809907711538717,80.9907711538717,BBH,0.654669943237205,50.1851331844035,MATH Level 5,0.253021148036254,25.3021148036254,GPQA,0.286912751677852,4.92170022371365,MUSR,0.415364583333333,10.9205729166667,MMLU-PRO,0.520694813829787,46.7438682033097,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-17,2024-06-12,1,meta-llama/Meta-Llama-3-70B,llama3,1439,70.554,18.2391501177391 -meta-llama/Meta-Llama-3-8B_bfloat16_62bd457b6fe961a42a631306577e622c83876cb6_False,meta-llama/Meta-Llama-3-8B,62bd457b6fe961a42a631306577e622c83876cb6,bfloat16,pretrained,Original,LlamaForCausalLM,13.4632115530557,FALSE,IFEval,0.145506145915061,14.5506145915061,BBH,0.459790519524026,24.500763796768,MATH Level 5,0.0354984894259819,3.54984894259819,GPQA,0.305369127516779,7.38255033557047,MUSR,0.36140625,6.24244791666667,MMLU-PRO,0.320977393617021,24.5530437352246,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-17,2024-06-12,0,meta-llama/Meta-Llama-3-8B,llama3,5907,8.03,0.87256849761081 -meta-llama/Meta-Llama-3-8B-Instruct_bfloat16_e1945c40cd546c78e41f1151f4db032b271faeaa_True,meta-llama/Meta-Llama-3-8B-Instruct,e1945c40cd546c78e41f1151f4db032b271faeaa,bfloat16,chatmodels,Original,LlamaForCausalLM,23.9087356939368,TRUE,IFEval,0.740839860459137,74.0839860459137,BBH,0.498871111361695,28.2449495763436,MATH Level 5,0.0868580060422961,8.68580060422961,GPQA,0.259228187919463,1.23042505592841,MUSR,0.356822916666667,1.60286458333334,MMLU-PRO,0.366439494680851,29.6043882978723,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-17,2024-06-12,0,meta-llama/Meta-Llama-3-8B-Instruct,llama3,3690,8.03,0.797499677890947 -meta-llama/Meta-Llama-3-8B-Instruct_float16_e1945c40cd546c78e41f1151f4db032b271faeaa_False,meta-llama/Meta-Llama-3-8B-Instruct,e1945c40cd546c78e41f1151f4db032b271faeaa,float16,chatmodels,Original,LlamaForCausalLM,20.5965713292081,FALSE,IFEval,0.478232201669349,47.8232201669349,BBH,0.491026417512868,26.7952835025737,MATH Level 5,0.0906344410876133,9.06344410876133,GPQA,0.292785234899329,5.70469798657718,MUSR,0.380541666666667,5.40104166666667,MMLU-PRO,0.359125664893617,28.7917405437352,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-17,2024-07-08,0,meta-llama/Meta-Llama-3-8B-Instruct,llama3,3690,8.03,0.949473257188463 +meta-llama/Llama-2-70b-chat-hf_float16_e9149a12809580e8602995856f8098ce973d1080_True,meta-llama/Llama-2-70b-chat-hf,e9149a12809580e8602995856f8098ce973d1080,float16,chatmodels,Original,LlamaForCausalLM,12.7464047385667,TRUE,IFEval,0.495792275606502,49.5792275606502,BBH,0.304247414616427,4.61376708259061,MATH Level 5,0.00981873111782478,0.981873111782478,GPQA,0.264261744966443,1.90156599552573,MUSR,0.368666666666667,3.48333333333334,MMLU-PRO,0.24326795212766,15.9186613475177,TRUE,FALSE,FALSE,FALSE,TRUE,2023-07-14,2024-06-12,0,meta-llama/Llama-2-70b-chat-hf,llama2,2165,68.977,22.8984550552606 +meta-llama/Llama-2-70b-hf_float16_3aba440b59558f995867ba6e1f58f21d0336b5bb_False,meta-llama/Llama-2-70b-hf,3aba440b59558f995867ba6e1f58f21d0336b5bb,float16,pretrained,Original,LlamaForCausalLM,18.3096580216144,FALSE,IFEval,0.240678067527494,24.0678067527494,BBH,0.547259119044934,35.9000618637217,MATH Level 5,0.0287009063444109,2.87009063444109,GPQA,0.302852348993289,7.04697986577182,MUSR,0.412354166666667,9.77760416666667,MMLU-PRO,0.371758643617021,30.1954048463357,TRUE,FALSE,FALSE,FALSE,TRUE,2023-07-11,2024-06-12,0,meta-llama/Llama-2-70b-hf,llama2,839,68.977,29.6212466171519 +meta-llama/Llama-2-7b-chat-hf_float16_f5db02db724555f92da89c216ac04704f23d4590_True,meta-llama/Llama-2-7b-chat-hf,f5db02db724555f92da89c216ac04704f23d4590,float16,pretrained,Original,LlamaForCausalLM,9.39548527825095,TRUE,IFEval,0.398647810032935,39.8647810032935,BBH,0.311354635500219,4.45917164595948,MATH Level 5,0.006797583081571,0.6797583081571,GPQA,0.253355704697987,0.447427293064876,MUSR,0.367552083333333,3.27734375,MMLU-PRO,0.168799867021277,7.64442966903073,TRUE,FALSE,FALSE,FALSE,TRUE,2023-07-13,2024-08-30,0,meta-llama/Llama-2-7b-chat-hf,llama2,4064,6.738,1.15687903615516 +meta-llama/Llama-2-7b-hf_float16_01c7f73d771dfac7d292323805ebc428287df4f9_False,meta-llama/Llama-2-7b-hf,01c7f73d771dfac7d292323805ebc428287df4f9,float16,pretrained,Original,LlamaForCausalLM,8.73082889563367,FALSE,IFEval,0.251893863836842,25.1893863836842,BBH,0.349619581998218,10.351416657849,MATH Level 5,0.0128398791540786,1.28398791540786,GPQA,0.266778523489933,2.23713646532438,MUSR,0.3700625,3.7578125,MMLU-PRO,0.18608710106383,9.56523345153664,TRUE,FALSE,FALSE,FALSE,TRUE,2023-07-13,2024-06-12,0,meta-llama/Llama-2-7b-hf,llama2,1844,6.738,0.563094562772064 +meta-llama/Llama-3.1-8B_float16_d04e592bb4f6aa9cfee91e2e20afa771667e1d4b_False,meta-llama/Llama-3.1-8B,d04e592bb4f6aa9cfee91e2e20afa771667e1d4b,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,14.2194553235834,FALSE,IFEval,0.124598288097803,12.4598288097803,BBH,0.465959054460073,25.3044706347549,MATH Level 5,0.0536253776435045,5.36253776435045,GPQA,0.310402684563758,8.05369127516779,MUSR,0.3811875,8.71510416666667,MMLU-PRO,0.328789893617021,25.4210992907801,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-14,2024-12-07,0,meta-llama/Llama-3.1-8B,llama3.1,1193,8.03,0.713243580943846 +meta-llama/Llama-3.2-1B_bfloat16_a7c18587d7f473bfea02aa5639aa349403307b54_False,meta-llama/Llama-3.2-1B,a7c18587d7f473bfea02aa5639aa349403307b54,bfloat16,pretrained,Original,LlamaForCausalLM,4.03149449541509,FALSE,IFEval,0.147779004153424,14.7779004153424,BBH,0.311495409646081,4.36602965655676,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.228187919463087,0,MUSR,0.344729166666667,2.5578125,MMLU-PRO,0.120345744680851,2.26063829787234,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-18,2024-09-23,0,meta-llama/Llama-3.2-1B,llama3.2,1252,1.24,0.41912851784102 +meta-llama/Llama-3.2-1B-Instruct_bfloat16_d0a2081ed47e20ce524e8bc5d132f3fad2f69ff0_True,meta-llama/Llama-3.2-1B-Instruct,d0a2081ed47e20ce524e8bc5d132f3fad2f69ff0,bfloat16,chatmodels,Original,LlamaForCausalLM,13.8137204928249,TRUE,IFEval,0.569831380736446,56.9831380736446,BBH,0.349684980617683,8.74252131230305,MATH Level 5,0.0324773413897281,3.24773413897281,GPQA,0.275167785234899,3.35570469798658,MUSR,0.332854166666667,2.9734375,MMLU-PRO,0.168218085106383,7.57978723404255,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-18,2024-09-23,0,meta-llama/Llama-3.2-1B-Instruct,llama3.2,633,1.24,0.404904524907622 +meta-llama/Llama-3.2-3B_bfloat16_95c102307f55fbd6d18ddf28bfbcb537ffdc2806_False,meta-llama/Llama-3.2-3B,95c102307f55fbd6d18ddf28bfbcb537ffdc2806,bfloat16,pretrained,Original,LlamaForCausalLM,8.5845296652033,FALSE,IFEval,0.133740696906431,13.374069690643,BBH,0.390511711699106,14.2326648843641,MATH Level 5,0.0120845921450151,1.20845921450151,GPQA,0.26761744966443,2.3489932885906,MUSR,0.35771875,3.81484375,MMLU-PRO,0.248753324468085,16.5281471631206,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-18,2024-09-27,0,meta-llama/Llama-3.2-3B,llama3.2,401,3.213,1.33181264899492 +meta-llama/Llama-3.2-3B-Instruct_bfloat16_276b29ce8303c9b88966a9b32fc75692dce4d8e1_True,meta-llama/Llama-3.2-3B-Instruct,276b29ce8303c9b88966a9b32fc75692dce4d8e1,bfloat16,chatmodels,Original,LlamaForCausalLM,24.1165339900694,TRUE,IFEval,0.739316125657699,73.9316125657699,BBH,0.461007023946607,24.0591864468855,MATH Level 5,0.171450151057402,17.1450151057402,GPQA,0.278523489932886,3.80313199105145,MUSR,0.352854166666667,1.3734375,MMLU-PRO,0.319481382978723,24.3868203309693,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-18,2024-09-27,0,meta-llama/Llama-3.2-3B-Instruct,llama3.2,779,3.213,1.27120351986613 +meta-llama/Llama-3.3-70B-Instruct_bfloat16__False,meta-llama/Llama-3.3-70B-Instruct,"",bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,36.8288410384085,FALSE,IFEval,0.899758197139146,89.9758197139146,BBH,0.691931282832581,56.5614107880222,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.328859060402685,10.5145413870246,MUSR,0.446125,15.565625,MMLU-PRO,0.533161569148936,48.1290632387707,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-26,2024-12-09,1,meta-llama/Llama-3.3-70B-Instruct (Merge),llama3.3,984,70.554,38.2795370537265 +meta-llama/Meta-Llama-3-70B_bfloat16_b4d08b7db49d488da3ac49adf25a6b9ac01ae338_False,meta-llama/Meta-Llama-3-70B,b4d08b7db49d488da3ac49adf25a6b9ac01ae338,bfloat16,pretrained,Original,LlamaForCausalLM,26.6675858211602,FALSE,IFEval,0.160319064526567,16.0319064526567,BBH,0.646107459990447,48.7098126475059,MATH Level 5,0.183534743202417,18.3534743202417,GPQA,0.397651006711409,19.6868008948546,MUSR,0.451822916666667,16.0111979166667,MMLU-PRO,0.470910904255319,41.2123226950355,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-17,2024-06-12,0,meta-llama/Meta-Llama-3-70B,llama3,836,70.554,23.4071857793614 +meta-llama/Meta-Llama-3-70B-Instruct_bfloat16_7129260dd854a80eb10ace5f61c20324b472b31c_True,meta-llama/Meta-Llama-3-70B-Instruct,7129260dd854a80eb10ace5f61c20324b472b31c,bfloat16,chatmodels,Original,LlamaForCausalLM,36.5106934142651,TRUE,IFEval,0.809907711538717,80.9907711538717,BBH,0.654669943237205,50.1851331844035,MATH Level 5,0.253021148036254,25.3021148036254,GPQA,0.286912751677852,4.92170022371365,MUSR,0.415364583333333,10.9205729166667,MMLU-PRO,0.520694813829787,46.7438682033097,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-17,2024-06-12,1,meta-llama/Meta-Llama-3-70B,llama3,1440,70.554,18.2391501177391 +meta-llama/Meta-Llama-3-8B_bfloat16_62bd457b6fe961a42a631306577e622c83876cb6_False,meta-llama/Meta-Llama-3-8B,62bd457b6fe961a42a631306577e622c83876cb6,bfloat16,pretrained,Original,LlamaForCausalLM,13.4632115530557,FALSE,IFEval,0.145506145915061,14.5506145915061,BBH,0.459790519524026,24.500763796768,MATH Level 5,0.0354984894259819,3.54984894259819,GPQA,0.305369127516779,7.38255033557047,MUSR,0.36140625,6.24244791666667,MMLU-PRO,0.320977393617021,24.5530437352246,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-17,2024-06-12,0,meta-llama/Meta-Llama-3-8B,llama3,5909,8.03,0.87256849761081 +meta-llama/Meta-Llama-3-8B-Instruct_bfloat16_e1945c40cd546c78e41f1151f4db032b271faeaa_True,meta-llama/Meta-Llama-3-8B-Instruct,e1945c40cd546c78e41f1151f4db032b271faeaa,bfloat16,chatmodels,Original,LlamaForCausalLM,23.9087356939368,TRUE,IFEval,0.740839860459137,74.0839860459137,BBH,0.498871111361695,28.2449495763436,MATH Level 5,0.0868580060422961,8.68580060422961,GPQA,0.259228187919463,1.23042505592841,MUSR,0.356822916666667,1.60286458333334,MMLU-PRO,0.366439494680851,29.6043882978723,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-17,2024-06-12,0,meta-llama/Meta-Llama-3-8B-Instruct,llama3,3691,8.03,0.797499677890947 +meta-llama/Meta-Llama-3-8B-Instruct_float16_e1945c40cd546c78e41f1151f4db032b271faeaa_False,meta-llama/Meta-Llama-3-8B-Instruct,e1945c40cd546c78e41f1151f4db032b271faeaa,float16,chatmodels,Original,LlamaForCausalLM,20.5965713292081,FALSE,IFEval,0.478232201669349,47.8232201669349,BBH,0.491026417512868,26.7952835025737,MATH Level 5,0.0906344410876133,9.06344410876133,GPQA,0.292785234899329,5.70469798657718,MUSR,0.380541666666667,5.40104166666667,MMLU-PRO,0.359125664893617,28.7917405437352,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-17,2024-07-08,0,meta-llama/Meta-Llama-3-8B-Instruct,llama3,3691,8.03,0.949473257188463 meta-llama/Meta-Llama-3.1-70B_bfloat16_f7d3cc45ed4ff669a354baf2e0f05e65799a0bee_True,meta-llama/Meta-Llama-3.1-70B,f7d3cc45ed4ff669a354baf2e0f05e65799a0bee,bfloat16,pretrained,Original,LlamaForCausalLM,26.2002158433759,TRUE,IFEval,0.168437523548629,16.8437523548629,BBH,0.626006918317161,46.3994129558189,MATH Level 5,0.18429003021148,18.429003021148,GPQA,0.38758389261745,18.34451901566,MUSR,0.4571875,16.5817708333333,MMLU-PRO,0.465425531914894,40.6028368794326,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-14,2024-07-23,0,meta-llama/Meta-Llama-3.1-70B,llama3.1,319,70.554,13.6018520327186 meta-llama/Meta-Llama-3.1-70B-Instruct_bfloat16_b9461463b511ed3c0762467538ea32cf7c9669f2_True,meta-llama/Meta-Llama-3.1-70B-Instruct,b9461463b511ed3c0762467538ea32cf7c9669f2,bfloat16,chatmodels,Original,LlamaForCausalLM,42.1763127975088,TRUE,IFEval,0.866885419575615,86.6885419575615,BBH,0.691728745366365,55.9279917389847,MATH Level 5,0.306646525679758,30.6646525679758,GPQA,0.356543624161074,14.2058165548098,MUSR,0.4580625,17.6911458333333,MMLU-PRO,0.530917553191489,47.8797281323877,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-16,2024-08-15,1,meta-llama/Meta-Llama-3.1-70B,llama3.1,748,70.554,26.8020157168701 -meta-llama/Meta-Llama-3.1-8B_bfloat16_e5c39e551424c763dbc3e58e32ef2999d33a6d8d_True,meta-llama/Meta-Llama-3.1-8B,e5c39e551424c763dbc3e58e32ef2999d33a6d8d,bfloat16,pretrained,Original,LlamaForCausalLM,13.8690662612791,TRUE,IFEval,0.126996369632575,12.6996369632575,BBH,0.4666136555004,25.2947798510872,MATH Level 5,0.0513595166163142,5.13595166163142,GPQA,0.296140939597315,6.15212527964205,MUSR,0.382520833333333,8.98177083333333,MMLU-PRO,0.324551196808511,24.9501329787234,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-14,2024-07-23,0,meta-llama/Meta-Llama-3.1-8B,llama3.1,1191,8.03,3.5985230038683 -meta-llama/Meta-Llama-3.1-8B-Instruct_bfloat16_df34336b42332c6d360959e259cd6271c6a09fd4_True,meta-llama/Meta-Llama-3.1-8B-Instruct,df34336b42332c6d360959e259cd6271c6a09fd4,bfloat16,chatmodels,Original,LlamaForCausalLM,28.2044584981019,TRUE,IFEval,0.785577822400121,78.5577822400121,BBH,0.507326783896146,29.8927563524528,MATH Level 5,0.193353474320242,19.3353474320242,GPQA,0.26761744966443,2.3489932885906,MUSR,0.386989583333333,8.40703125,MMLU-PRO,0.376163563829787,30.6848404255319,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-18,2024-08-15,1,meta-llama/Meta-Llama-3.1-8B,llama3.1,3258,8.03,2.48701186834409 +meta-llama/Meta-Llama-3.1-8B_bfloat16_e5c39e551424c763dbc3e58e32ef2999d33a6d8d_True,meta-llama/Meta-Llama-3.1-8B,e5c39e551424c763dbc3e58e32ef2999d33a6d8d,bfloat16,pretrained,Original,LlamaForCausalLM,13.8690662612791,TRUE,IFEval,0.126996369632575,12.6996369632575,BBH,0.4666136555004,25.2947798510872,MATH Level 5,0.0513595166163142,5.13595166163142,GPQA,0.296140939597315,6.15212527964205,MUSR,0.382520833333333,8.98177083333333,MMLU-PRO,0.324551196808511,24.9501329787234,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-14,2024-07-23,0,meta-llama/Meta-Llama-3.1-8B,llama3.1,1193,8.03,3.5985230038683 +meta-llama/Meta-Llama-3.1-8B-Instruct_bfloat16_df34336b42332c6d360959e259cd6271c6a09fd4_True,meta-llama/Meta-Llama-3.1-8B-Instruct,df34336b42332c6d360959e259cd6271c6a09fd4,bfloat16,chatmodels,Original,LlamaForCausalLM,28.2044584981019,TRUE,IFEval,0.785577822400121,78.5577822400121,BBH,0.507326783896146,29.8927563524528,MATH Level 5,0.193353474320242,19.3353474320242,GPQA,0.26761744966443,2.3489932885906,MUSR,0.386989583333333,8.40703125,MMLU-PRO,0.376163563829787,30.6848404255319,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-18,2024-08-15,1,meta-llama/Meta-Llama-3.1-8B,llama3.1,3261,8.03,2.48701186834409 microsoft/DialoGPT-medium_bfloat16_7b40bb0f92c45fefa957d088000d8648e5c7fa33_True,microsoft/DialoGPT-medium,7b40bb0f92c45fefa957d088000d8648e5c7fa33,bfloat16,chatmodels,Original,GPT2LMHeadModel,5.25143360679031,TRUE,IFEval,0.147904227449833,14.7904227449833,BBH,0.301415638014199,2.55685577233522,MATH Level 5,0,0,GPQA,0.254194630872483,0.559284116331097,MUSR,0.428666666666667,12.2833333333333,MMLU-PRO,0.11186835106383,1.31870567375887,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-13,0,microsoft/DialoGPT-medium,mit,334,0.345,0.129464485100266 microsoft/Orca-2-13b_bfloat16_2539ff53e6baa4cc603774ad5a2d646f4041ea4e_False,microsoft/Orca-2-13b,2539ff53e6baa4cc603774ad5a2d646f4041ea4e,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,18.1494038209109,FALSE,IFEval,0.31279338820995,31.279338820995,BBH,0.488448972883961,27.3080194999426,MATH Level 5,0.0105740181268882,1.05740181268882,GPQA,0.280201342281879,4.0268456375839,MUSR,0.51296875,25.7877604166667,MMLU-PRO,0.274933510638298,19.4370567375887,TRUE,FALSE,FALSE,FALSE,TRUE,2023-11-14,2024-06-12,0,microsoft/Orca-2-13b,other,665,13,1.00858169959549 microsoft/Orca-2-7b_bfloat16_60e31e6bdcf582ad103b807cb74b73ee1d2c4b17_False,microsoft/Orca-2-7b,60e31e6bdcf582ad103b807cb74b73ee1d2c4b17,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,14.2160083291346,FALSE,IFEval,0.218346210277619,21.8346210277619,BBH,0.445213226754594,22.4294684028185,MATH Level 5,0.00830815709969789,0.830815709969789,GPQA,0.260906040268456,1.45413870246085,MUSR,0.502614583333333,24.0934895833333,MMLU-PRO,0.23188164893617,14.6535165484634,TRUE,FALSE,FALSE,FALSE,TRUE,2023-11-14,2024-06-12,0,microsoft/Orca-2-7b,other,216,7,1.20931193274994 microsoft/Phi-3-medium-128k-instruct_bfloat16_fa7d2aa4f5ea69b2e36b20d050cdae79c9bfbb3f_True,microsoft/Phi-3-medium-128k-instruct,fa7d2aa4f5ea69b2e36b20d050cdae79c9bfbb3f,bfloat16,chatmodels,Original,Phi3ForCausalLM,31.7116532556656,TRUE,IFEval,0.604002934436185,60.4002934436185,BBH,0.638232253087055,48.4604512739902,MATH Level 5,0.172960725075529,17.2960725075529,GPQA,0.336409395973154,11.5212527964206,MUSR,0.412947916666667,11.3518229166667,MMLU-PRO,0.471160239361702,41.2400265957447,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-07,2024-08-21,0,microsoft/Phi-3-medium-128k-instruct,mit,371,13.96,1.94755874452617 microsoft/Phi-3-medium-4k-instruct_bfloat16_d194e4e74ffad5a5e193e26af25bcfc80c7f1ffc_True,microsoft/Phi-3-medium-4k-instruct,d194e4e74ffad5a5e193e26af25bcfc80c7f1ffc,bfloat16,chatmodels,Original,Phi3ForCausalLM,32.8962495702928,TRUE,IFEval,0.642271395452954,64.2271395452954,BBH,0.641246489055555,49.3806100742202,MATH Level 5,0.183534743202417,18.3534743202417,GPQA,0.336409395973154,11.5212527964206,MUSR,0.42575,13.0520833333333,MMLU-PRO,0.467586436170213,40.8429373522459,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-07,2024-06-12,0,microsoft/Phi-3-medium-4k-instruct,mit,211,13.96,1.45526252332937 -microsoft/Phi-3-mini-128k-instruct_bfloat16_5be6479b4bc06a081e8f4c6ece294241ccd32dec_True,microsoft/Phi-3-mini-128k-instruct,5be6479b4bc06a081e8f4c6ece294241ccd32dec,bfloat16,chatmodels,Original,Phi3ForCausalLM,25.6262872732554,TRUE,IFEval,0.597633168880792,59.7633168880792,BBH,0.557453179267985,37.0997666322403,MATH Level 5,0.0974320241691843,9.74320241691843,GPQA,0.317953020134228,9.06040268456376,MUSR,0.3936875,7.7109375,MMLU-PRO,0.373420877659575,30.3800975177305,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-22,2024-08-21,0,microsoft/Phi-3-mini-128k-instruct,mit,1610,3.821,24.2222515926888 -microsoft/Phi-3-mini-4k-instruct_bfloat16_ff07dc01615f8113924aed013115ab2abd32115b_True,microsoft/Phi-3-mini-4k-instruct,ff07dc01615f8113924aed013115ab2abd32115b,bfloat16,chatmodels,Original,Phi3ForCausalLM,25.9677326380416,TRUE,IFEval,0.561288492311511,56.1288492311511,BBH,0.567597262633488,39.2693352377728,MATH Level 5,0.11631419939577,11.631419939577,GPQA,0.319630872483222,9.2841163310962,MUSR,0.395020833333333,7.64427083333334,MMLU-PRO,0.386635638297872,31.8484042553192,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-22,2024-06-12,0,microsoft/Phi-3-mini-4k-instruct,mit,1087,3.821,0.804074829912372 -microsoft/Phi-3-mini-4k-instruct_float16_c1358f8a35e6d2af81890deffbbfa575b978c62f_True,microsoft/Phi-3-mini-4k-instruct,c1358f8a35e6d2af81890deffbbfa575b978c62f,float16,chatmodels,Original,Phi3ForCausalLM,27.4111166417796,TRUE,IFEval,0.547674614467391,54.7674614467391,BBH,0.549071891949582,36.5598553051879,MATH Level 5,0.154833836858006,15.4833836858006,GPQA,0.332214765100671,10.9619686800895,MUSR,0.428416666666667,13.11875,MMLU-PRO,0.402177526595745,33.5752807328605,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-22,2024-07-02,0,microsoft/Phi-3-mini-4k-instruct,mit,1087,3.821,0.786699265454341 +microsoft/Phi-3-mini-128k-instruct_bfloat16_5be6479b4bc06a081e8f4c6ece294241ccd32dec_True,microsoft/Phi-3-mini-128k-instruct,5be6479b4bc06a081e8f4c6ece294241ccd32dec,bfloat16,chatmodels,Original,Phi3ForCausalLM,25.6262872732554,TRUE,IFEval,0.597633168880792,59.7633168880792,BBH,0.557453179267985,37.0997666322403,MATH Level 5,0.0974320241691843,9.74320241691843,GPQA,0.317953020134228,9.06040268456376,MUSR,0.3936875,7.7109375,MMLU-PRO,0.373420877659575,30.3800975177305,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-22,2024-08-21,0,microsoft/Phi-3-mini-128k-instruct,mit,1611,3.821,24.2222515926888 +microsoft/Phi-3-mini-4k-instruct_bfloat16_ff07dc01615f8113924aed013115ab2abd32115b_True,microsoft/Phi-3-mini-4k-instruct,ff07dc01615f8113924aed013115ab2abd32115b,bfloat16,chatmodels,Original,Phi3ForCausalLM,25.9677326380416,TRUE,IFEval,0.561288492311511,56.1288492311511,BBH,0.567597262633488,39.2693352377728,MATH Level 5,0.11631419939577,11.631419939577,GPQA,0.319630872483222,9.2841163310962,MUSR,0.395020833333333,7.64427083333334,MMLU-PRO,0.386635638297872,31.8484042553192,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-22,2024-06-12,0,microsoft/Phi-3-mini-4k-instruct,mit,1088,3.821,0.804074829912372 +microsoft/Phi-3-mini-4k-instruct_float16_c1358f8a35e6d2af81890deffbbfa575b978c62f_True,microsoft/Phi-3-mini-4k-instruct,c1358f8a35e6d2af81890deffbbfa575b978c62f,float16,chatmodels,Original,Phi3ForCausalLM,27.4111166417796,TRUE,IFEval,0.547674614467391,54.7674614467391,BBH,0.549071891949582,36.5598553051879,MATH Level 5,0.154833836858006,15.4833836858006,GPQA,0.332214765100671,10.9619686800895,MUSR,0.428416666666667,13.11875,MMLU-PRO,0.402177526595745,33.5752807328605,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-22,2024-07-02,0,microsoft/Phi-3-mini-4k-instruct,mit,1088,3.821,0.786699265454341 microsoft/Phi-3-small-128k-instruct_bfloat16_f80aaa30bfc64c2b8ab214b541d9050e97163bc4_True,microsoft/Phi-3-small-128k-instruct,f80aaa30bfc64c2b8ab214b541d9050e97163bc4,bfloat16,chatmodels,Original,Phi3SmallForCausalLM,28.5909915695228,TRUE,IFEval,0.636825844315306,63.6825844315306,BBH,0.620217677869698,45.6340696414479,MATH Level 5,0,0,GPQA,0.317114093959732,8.94854586129754,MUSR,0.43784375,14.4971354166667,MMLU-PRO,0.449052526595745,38.7836140661939,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-07,2024-06-13,0,microsoft/Phi-3-small-128k-instruct,mit,172,7.392,2.50846790619425 microsoft/Phi-3-small-8k-instruct_bfloat16_1535ae26fb4faada95c6950e8bc6e867cdad6b00_True,microsoft/Phi-3-small-8k-instruct,1535ae26fb4faada95c6950e8bc6e867cdad6b00,bfloat16,chatmodels,Original,Phi3SmallForCausalLM,29.6709218521057,TRUE,IFEval,0.649665110794913,64.9665110794913,BBH,0.620836488087056,46.2055703663891,MATH Level 5,0.0284301430770108,2.84301430770108,GPQA,0.312080536912752,8.27740492170022,MUSR,0.455791666666667,16.7739583333333,MMLU-PRO,0.45063164893617,38.9590721040189,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-07,2024-06-13,0,microsoft/Phi-3-small-8k-instruct,mit,159,7.392,1.0254536035218 -microsoft/Phi-3.5-MoE-instruct_bfloat16_482a9ba0eb0e1fa1671e3560e009d7cec2e5147c_True,microsoft/Phi-3.5-MoE-instruct,482a9ba0eb0e1fa1671e3560e009d7cec2e5147c,bfloat16,chatmodels,Original,Phi3ForCausalLM,35.4565075216065,TRUE,IFEval,0.692454908531585,69.2454908531585,BBH,0.640762564622586,48.7746463593219,MATH Level 5,0.226586102719033,22.6586102719033,GPQA,0.355704697986577,14.0939597315436,MUSR,0.456479166666667,17.3265625,MMLU-PRO,0.465757978723404,40.6397754137116,TRUE,FALSE,TRUE,FALSE,TRUE,2024-08-17,2024-08-21,0,microsoft/Phi-3.5-MoE-instruct,mit,531,42,4.63227861394431 -microsoft/Phi-3.5-mini-instruct_bfloat16_64963004ad95869fa73a30279371c8778509ac84_True,microsoft/Phi-3.5-mini-instruct,64963004ad95869fa73a30279371c8778509ac84,bfloat16,chatmodels,Original,Phi3ForCausalLM,27.5675734687961,TRUE,IFEval,0.577450054743636,57.7450054743636,BBH,0.551778512611196,36.7458539085166,MATH Level 5,0.159365558912387,15.9365558912387,GPQA,0.339765100671141,11.9686800894855,MUSR,0.402125,10.0989583333333,MMLU-PRO,0.396193484042553,32.9103871158392,TRUE,FALSE,FALSE,FALSE,TRUE,2024-08-16,2024-08-21,0,microsoft/Phi-3.5-mini-instruct,mit,682,3.821,3.69600430233737 +microsoft/Phi-3.5-MoE-instruct_bfloat16_482a9ba0eb0e1fa1671e3560e009d7cec2e5147c_True,microsoft/Phi-3.5-MoE-instruct,482a9ba0eb0e1fa1671e3560e009d7cec2e5147c,bfloat16,chatmodels,Original,Phi3ForCausalLM,35.4565075216065,TRUE,IFEval,0.692454908531585,69.2454908531585,BBH,0.640762564622586,48.7746463593219,MATH Level 5,0.226586102719033,22.6586102719033,GPQA,0.355704697986577,14.0939597315436,MUSR,0.456479166666667,17.3265625,MMLU-PRO,0.465757978723404,40.6397754137116,TRUE,FALSE,TRUE,FALSE,TRUE,2024-08-17,2024-08-21,0,microsoft/Phi-3.5-MoE-instruct,mit,533,42,4.63227861394431 +microsoft/Phi-3.5-mini-instruct_bfloat16_64963004ad95869fa73a30279371c8778509ac84_True,microsoft/Phi-3.5-mini-instruct,64963004ad95869fa73a30279371c8778509ac84,bfloat16,chatmodels,Original,Phi3ForCausalLM,27.5675734687961,TRUE,IFEval,0.577450054743636,57.7450054743636,BBH,0.551778512611196,36.7458539085166,MATH Level 5,0.159365558912387,15.9365558912387,GPQA,0.339765100671141,11.9686800894855,MUSR,0.402125,10.0989583333333,MMLU-PRO,0.396193484042553,32.9103871158392,TRUE,FALSE,FALSE,FALSE,TRUE,2024-08-16,2024-08-21,0,microsoft/Phi-3.5-mini-instruct,mit,686,3.821,3.69600430233737 microsoft/phi-1_bfloat16_b9ac0e6d78d43970ecf88e9e0154b3a7da20ed89_False,microsoft/phi-1,b9ac0e6d78d43970ecf88e9e0154b3a7da20ed89,bfloat16,pretrained,Original,PhiForCausalLM,5.52396572810627,FALSE,IFEval,0.206805719934219,20.6805719934219,BBH,0.313947558958378,4.27399921221468,MATH Level 5,0.006797583081571,0.6797583081571,GPQA,0.26510067114094,2.01342281879195,MUSR,0.352510416666667,3.69713541666667,MMLU-PRO,0.116190159574468,1.79890661938534,TRUE,FALSE,FALSE,FALSE,TRUE,2023-09-10,2024-06-13,0,microsoft/phi-1,mit,207,1.418,0.28622924752808 -microsoft/phi-1_5_float16_675aa382d814580b22651a30acb1a585d7c25963_False,microsoft/phi-1_5,675aa382d814580b22651a30acb1a585d7c25963,float16,pretrained,Original,PhiForCausalLM,7.05767379443971,FALSE,IFEval,0.203283953244059,20.3283953244059,BBH,0.335975832119967,7.46893877007024,MATH Level 5,0.0113293051359517,1.13293051359517,GPQA,0.26761744966443,2.3489932885906,MUSR,0.340416666666667,3.38541666666667,MMLU-PRO,0.169132313829787,7.68136820330969,TRUE,FALSE,FALSE,FALSE,TRUE,2023-09-10,2024-06-09,0,microsoft/phi-1_5,mit,1317,1.418,0.340862069057633 -microsoft/phi-2_float16_ef382358ec9e382308935a992d908de099b64c23_False,microsoft/phi-2,ef382358ec9e382308935a992d908de099b64c23,float16,pretrained,Original,PhiForCausalLM,15.4713509741263,FALSE,IFEval,0.273875539125077,27.3875539125077,BBH,0.48812087712497,28.0385192934393,MATH Level 5,0.0256797583081571,2.56797583081571,GPQA,0.271812080536913,2.9082774049217,MUSR,0.409895833333333,13.8369791666667,MMLU-PRO,0.26279920212766,18.0888002364066,TRUE,FALSE,FALSE,FALSE,TRUE,2023-12-13,2024-06-09,0,microsoft/phi-2,mit,3251,2.78,0.423520982590239 +microsoft/phi-1_5_float16_675aa382d814580b22651a30acb1a585d7c25963_False,microsoft/phi-1_5,675aa382d814580b22651a30acb1a585d7c25963,float16,pretrained,Original,PhiForCausalLM,7.05767379443971,FALSE,IFEval,0.203283953244059,20.3283953244059,BBH,0.335975832119967,7.46893877007024,MATH Level 5,0.0113293051359517,1.13293051359517,GPQA,0.26761744966443,2.3489932885906,MUSR,0.340416666666667,3.38541666666667,MMLU-PRO,0.169132313829787,7.68136820330969,TRUE,FALSE,FALSE,FALSE,TRUE,2023-09-10,2024-06-09,0,microsoft/phi-1_5,mit,1318,1.418,0.340862069057633 +microsoft/phi-2_float16_ef382358ec9e382308935a992d908de099b64c23_False,microsoft/phi-2,ef382358ec9e382308935a992d908de099b64c23,float16,pretrained,Original,PhiForCausalLM,15.4713509741263,FALSE,IFEval,0.273875539125077,27.3875539125077,BBH,0.48812087712497,28.0385192934393,MATH Level 5,0.0256797583081571,2.56797583081571,GPQA,0.271812080536913,2.9082774049217,MUSR,0.409895833333333,13.8369791666667,MMLU-PRO,0.26279920212766,18.0888002364066,TRUE,FALSE,FALSE,FALSE,TRUE,2023-12-13,2024-06-09,0,microsoft/phi-2,mit,3252,2.78,0.423520982590239 migtissera/Llama-3-70B-Synthia-v3.5_float16_8744db0bccfc18f1847633da9d29fc89b35b4190_True,migtissera/Llama-3-70B-Synthia-v3.5,8744db0bccfc18f1847633da9d29fc89b35b4190,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,35.2042985630762,TRUE,IFEval,0.607649924422754,60.7649924422754,BBH,0.648863802627128,49.1181596957482,MATH Level 5,0.189577039274924,18.9577039274924,GPQA,0.38758389261745,18.34451901566,MUSR,0.492197916666667,23.39140625,MMLU-PRO,0.465841090425532,40.6490100472813,TRUE,FALSE,FALSE,FALSE,FALSE,2024-05-26,2024-08-28,0,migtissera/Llama-3-70B-Synthia-v3.5,llama3,5,70.554,8.76969798956 migtissera/Llama-3-8B-Synthia-v3.5_float16_af4990801a24fee7acf16370cb5aa5643b5e9d6c_True,migtissera/Llama-3-8B-Synthia-v3.5,af4990801a24fee7acf16370cb5aa5643b5e9d6c,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,19.6966778088349,TRUE,IFEval,0.506958204231439,50.6958204231439,BBH,0.488794093366004,27.5423394300577,MATH Level 5,0.0506042296072508,5.06042296072508,GPQA,0.271812080536913,2.9082774049217,MUSR,0.404385416666667,9.41484375,MMLU-PRO,0.303025265957447,22.5583628841608,TRUE,FALSE,FALSE,FALSE,FALSE,2024-05-17,2024-08-28,0,migtissera/Llama-3-8B-Synthia-v3.5,llama3,15,8.03,0.828698366274131 migtissera/Tess-3-7B-SFT_bfloat16_404de3b56564dbd43cd64d97f8574b43189462f3_True,migtissera/Tess-3-7B-SFT,404de3b56564dbd43cd64d97f8574b43189462f3,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,17.0961631507225,TRUE,IFEval,0.394626258327903,39.4626258327903,BBH,0.460734838950762,24.123847398237,MATH Level 5,0.0332326283987915,3.32326283987915,GPQA,0.270973154362416,2.79642058165548,MUSR,0.411270833333333,10.2755208333333,MMLU-PRO,0.303357712765957,22.5953014184397,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-09,2024-07-20,1,mistralai/Mistral-7B-v0.3,apache-2.0,4,7.248,0.647169773785903 @@ -1643,21 +1643,21 @@ migtissera/Trinity-2-Codestral-22B_bfloat16_5f20b9d8af1a75c135c70bd7295e58301cce migtissera/Trinity-2-Codestral-22B-v0.2_float16_63513c3eb9b7c552fc163f58a2e7dc1fa09573b5_True,migtissera/Trinity-2-Codestral-22B-v0.2,63513c3eb9b7c552fc163f58a2e7dc1fa09573b5,float16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,21.8698250845993,TRUE,IFEval,0.434468321830521,43.4468321830521,BBH,0.568636468305542,37.6142460889593,MATH Level 5,0.0838368580060423,8.38368580060423,GPQA,0.300335570469799,6.71140939597315,MUSR,0.404479166666667,9.05989583333334,MMLU-PRO,0.334025930851064,26.0028812056738,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-13,2024-08-28,1,mistralai/Codestral-22B-v0.1,other,6,22.247,1.55352159287046 migtissera/Trinity-2-Codestral-22B-v0.2_bfloat16_9452a82ac7bfa9092a061ec913e9078ef3525a03_True,migtissera/Trinity-2-Codestral-22B-v0.2,9452a82ac7bfa9092a061ec913e9078ef3525a03,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,22.1117998201449,TRUE,IFEval,0.443011210255456,44.3011210255456,BBH,0.57064663561984,37.786041019572,MATH Level 5,0.0785498489425982,7.85498489425982,GPQA,0.307885906040268,7.71812080536913,MUSR,0.403145833333333,8.85989583333334,MMLU-PRO,0.335355718085106,26.1506353427896,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-13,2024-09-16,1,mistralai/Codestral-22B-v0.1,other,6,22.247,1.56120756866361 minghaowu/Qwen1.5-1.8B-OpenHermes-2.5_bfloat16_40700de82968350c192318877fe522630d0ef76d_True,minghaowu/Qwen1.5-1.8B-OpenHermes-2.5,40700de82968350c192318877fe522630d0ef76d,bfloat16,chatmodels,Original,Qwen2ForCausalLM,8.31969578816542,TRUE,IFEval,0.277797355461287,27.7797355461287,BBH,0.33746396801266,7.56147753424779,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.283557046979866,4.47427293064877,MUSR,0.352885416666667,1.07734375,MMLU-PRO,0.179188829787234,8.79875886524823,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-09-12,0,Removed,"",0,1.837,1.0949003455425 -ministral/Ministral-3b-instruct_bfloat16_2c95908929198d6e69af8638f0dbbd9bc6b93f9e_False,ministral/Ministral-3b-instruct,2c95908929198d6e69af8638f0dbbd9bc6b93f9e,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,3.38161348841134,FALSE,IFEval,0.13576421672274,13.576421672274,BBH,0.319185984783324,4.67586357856467,MATH Level 5,0,0,GPQA,0.251677852348993,0.223713646532442,MUSR,0.33825,0.78125,MMLU-PRO,0.109291888297872,1.03243203309693,TRUE,FALSE,FALSE,FALSE,FALSE,2024-03-14,2024-10-25,0,ministral/Ministral-3b-instruct,apache-2.0,34,3.316,0.264486930516462 +ministral/Ministral-3b-instruct_bfloat16_2c95908929198d6e69af8638f0dbbd9bc6b93f9e_False,ministral/Ministral-3b-instruct,2c95908929198d6e69af8638f0dbbd9bc6b93f9e,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,3.38161348841134,FALSE,IFEval,0.13576421672274,13.576421672274,BBH,0.319185984783324,4.67586357856467,MATH Level 5,0,0,GPQA,0.251677852348993,0.223713646532442,MUSR,0.33825,0.78125,MMLU-PRO,0.109291888297872,1.03243203309693,TRUE,FALSE,FALSE,FALSE,FALSE,2024-03-14,2024-10-25,0,ministral/Ministral-3b-instruct,apache-2.0,35,3.316,0.264486930516462 mistral-community/Mistral-7B-v0.2_bfloat16_2c3e624962b1a3f3fbf52e15969565caa7bc064a_False,mistral-community/Mistral-7B-v0.2,2c3e624962b1a3f3fbf52e15969565caa7bc064a,bfloat16,pretrained,Original,MistralForCausalLM,14.2153624426921,FALSE,IFEval,0.2266397602805,22.66397602805,BBH,0.451018796279758,23.9508653830296,MATH Level 5,0.0302114803625378,3.02114803625378,GPQA,0.291946308724832,5.59284116331097,MUSR,0.403177083333333,8.36380208333333,MMLU-PRO,0.295295877659575,21.6995419621749,TRUE,FALSE,FALSE,FALSE,TRUE,2024-03-23,2024-06-12,0,mistral-community/Mistral-7B-v0.2,apache-2.0,232,7.242,0.553213277920435 mistral-community/mixtral-8x22B-v0.3_bfloat16_211b177b79ab5ef245ee334d106c27623e786882_False,mistral-community/mixtral-8x22B-v0.3,211b177b79ab5ef245ee334d106c27623e786882,bfloat16,pretrained,Original,MixtralForCausalLM,25.789406608528,FALSE,IFEval,0.258263629392235,25.8263629392235,BBH,0.625000217843585,45.7310408976333,MATH Level 5,0.182779456193354,18.2779456193354,GPQA,0.37751677852349,17.0022371364653,MUSR,0.403697916666667,7.46223958333334,MMLU-PRO,0.463929521276596,40.4366134751773,TRUE,FALSE,TRUE,FALSE,TRUE,2024-05-25,2024-06-13,0,mistral-community/mixtral-8x22B-v0.3,apache-2.0,3,140.63,52.4944851685548 mistralai/Codestral-22B-v0.1_bfloat16_8f5fe23af91885222a1563283c87416745a5e212_True,mistralai/Codestral-22B-v0.1,8f5fe23af91885222a1563283c87416745a5e212,bfloat16,pretrained,Original,MistralForCausalLM,23.2799174068646,TRUE,IFEval,0.577175228393995,57.7175228393995,BBH,0.513913692100317,30.7376344119456,MATH Level 5,0.100453172205438,10.0453172205438,GPQA,0.298657718120805,6.48769574944072,MUSR,0.418708333333333,10.7385416666667,MMLU-PRO,0.315575132978723,23.9527925531915,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-29,2024-09-28,0,mistralai/Codestral-22B-v0.1,other,1156,22.247,1.3066695609381 -mistralai/Ministral-8B-Instruct-2410_bfloat16_199e57c1d66379760f6413f79d27008d1d1dbd6e_True,mistralai/Ministral-8B-Instruct-2410,199e57c1d66379760f6413f79d27008d1d1dbd6e,bfloat16,chatmodels,Original,MistralForCausalLM,22.0078589303086,TRUE,IFEval,0.589639933155139,58.963993315514,BBH,0.476164020168914,25.8247744094178,MATH Level 5,0.0649546827794562,6.49546827794562,GPQA,0.284395973154362,4.58612975391499,MUSR,0.41375,10.71875,MMLU-PRO,0.329122340425532,25.4580378250591,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-15,2024-12-01,0,mistralai/Ministral-8B-Instruct-2410,other,364,8.02,0.797086392156932 +mistralai/Ministral-8B-Instruct-2410_bfloat16_199e57c1d66379760f6413f79d27008d1d1dbd6e_True,mistralai/Ministral-8B-Instruct-2410,199e57c1d66379760f6413f79d27008d1d1dbd6e,bfloat16,chatmodels,Original,MistralForCausalLM,22.0078589303086,TRUE,IFEval,0.589639933155139,58.963993315514,BBH,0.476164020168914,25.8247744094178,MATH Level 5,0.0649546827794562,6.49546827794562,GPQA,0.284395973154362,4.58612975391499,MUSR,0.41375,10.71875,MMLU-PRO,0.329122340425532,25.4580378250591,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-15,2024-12-01,0,mistralai/Ministral-8B-Instruct-2410,other,363,8.02,0.797086392156932 mistralai/Mistral-7B-Instruct-v0.1_bfloat16_73068f3702d050a2fd5aa2ca1e612e5036429398_True,mistralai/Mistral-7B-Instruct-v0.1,73068f3702d050a2fd5aa2ca1e612e5036429398,bfloat16,chatmodels,Original,MistralForCausalLM,12.6957006941243,TRUE,IFEval,0.448706099815157,44.8706099815157,BBH,0.33548084759811,7.64702053582754,MATH Level 5,0.0181268882175227,1.81268882175227,GPQA,0.25,0,MUSR,0.384760416666667,6.12838541666667,MMLU-PRO,0.241439494680851,15.7154994089835,TRUE,FALSE,FALSE,FALSE,TRUE,2023-09-27,2024-06-27,1,mistralai/Mistral-7B-v0.1,apache-2.0,1537,7.242,1.21604471748007 -mistralai/Mistral-7B-Instruct-v0.2_bfloat16_41b61a33a2483885c981aa79e0df6b32407ed873_True,mistralai/Mistral-7B-Instruct-v0.2,41b61a33a2483885c981aa79e0df6b32407ed873,bfloat16,chatmodels,Original,MistralForCausalLM,18.4575391254667,TRUE,IFEval,0.549622778671702,54.9622778671702,BBH,0.445973552032928,22.9106019367136,MATH Level 5,0.027190332326284,2.7190332326284,GPQA,0.276006711409396,3.4675615212528,MUSR,0.396604166666667,7.60885416666667,MMLU-PRO,0.271692154255319,19.0769060283688,TRUE,FALSE,FALSE,FALSE,TRUE,2023-12-11,2024-06-12,0,mistralai/Mistral-7B-Instruct-v0.2,apache-2.0,2591,7.242,0.534406629050985 +mistralai/Mistral-7B-Instruct-v0.2_bfloat16_41b61a33a2483885c981aa79e0df6b32407ed873_True,mistralai/Mistral-7B-Instruct-v0.2,41b61a33a2483885c981aa79e0df6b32407ed873,bfloat16,chatmodels,Original,MistralForCausalLM,18.4575391254667,TRUE,IFEval,0.549622778671702,54.9622778671702,BBH,0.445973552032928,22.9106019367136,MATH Level 5,0.027190332326284,2.7190332326284,GPQA,0.276006711409396,3.4675615212528,MUSR,0.396604166666667,7.60885416666667,MMLU-PRO,0.271692154255319,19.0769060283688,TRUE,FALSE,FALSE,FALSE,TRUE,2023-12-11,2024-06-12,0,mistralai/Mistral-7B-Instruct-v0.2,apache-2.0,2593,7.242,0.534406629050985 mistralai/Mistral-7B-Instruct-v0.3_bfloat16_83e9aa141f2e28c82232fea5325f54edf17c43de_True,mistralai/Mistral-7B-Instruct-v0.3,83e9aa141f2e28c82232fea5325f54edf17c43de,bfloat16,chatmodels,Original,MistralForCausalLM,19.174746309635,TRUE,IFEval,0.546525441384416,54.6525441384416,BBH,0.472196317126484,25.569114948859,MATH Level 5,0.0354984894259819,3.54984894259819,GPQA,0.279362416107383,3.91498881431767,MUSR,0.37390625,4.30494791666667,MMLU-PRO,0.30751329787234,23.0570330969267,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-22,2024-06-12,1,mistralai/Mistral-7B-v0.3,apache-2.0,1180,7.248,0.5377834643891 -mistralai/Mistral-7B-v0.1_bfloat16_26bca36bde8333b5d7f72e9ed20ccda6a618af24_False,mistralai/Mistral-7B-v0.1,26bca36bde8333b5d7f72e9ed20ccda6a618af24,bfloat16,pretrained,Original,MistralForCausalLM,14.5626190834339,FALSE,IFEval,0.238554812342363,23.8554812342363,BBH,0.443106781218371,22.1684024578981,MATH Level 5,0.027190332326284,2.7190332326284,GPQA,0.291946308724832,5.59284116331097,MUSR,0.4139375,10.6755208333333,MMLU-PRO,0.301279920212766,22.3644355791962,TRUE,FALSE,FALSE,FALSE,TRUE,2023-09-20,2024-06-12,0,mistralai/Mistral-7B-v0.1,apache-2.0,3489,7.242,0.675534465568117 -mistralai/Mistral-7B-v0.3_bfloat16_b67d6a03ca097c5122fa65904fce0413500bf8c8_False,mistralai/Mistral-7B-v0.3,b67d6a03ca097c5122fa65904fce0413500bf8c8,bfloat16,pretrained,Original,MistralForCausalLM,14.2153624426921,FALSE,IFEval,0.2266397602805,22.66397602805,BBH,0.451018796279758,23.9508653830296,MATH Level 5,0.0302114803625378,3.02114803625378,GPQA,0.291946308724832,5.59284116331097,MUSR,0.403177083333333,8.36380208333333,MMLU-PRO,0.295295877659575,21.6995419621749,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-22,2024-06-12,0,mistralai/Mistral-7B-v0.3,apache-2.0,405,7.248,0.660475600081291 +mistralai/Mistral-7B-v0.1_bfloat16_26bca36bde8333b5d7f72e9ed20ccda6a618af24_False,mistralai/Mistral-7B-v0.1,26bca36bde8333b5d7f72e9ed20ccda6a618af24,bfloat16,pretrained,Original,MistralForCausalLM,14.5626190834339,FALSE,IFEval,0.238554812342363,23.8554812342363,BBH,0.443106781218371,22.1684024578981,MATH Level 5,0.027190332326284,2.7190332326284,GPQA,0.291946308724832,5.59284116331097,MUSR,0.4139375,10.6755208333333,MMLU-PRO,0.301279920212766,22.3644355791962,TRUE,FALSE,FALSE,FALSE,TRUE,2023-09-20,2024-06-12,0,mistralai/Mistral-7B-v0.1,apache-2.0,3490,7.242,0.675534465568117 +mistralai/Mistral-7B-v0.3_bfloat16_b67d6a03ca097c5122fa65904fce0413500bf8c8_False,mistralai/Mistral-7B-v0.3,b67d6a03ca097c5122fa65904fce0413500bf8c8,bfloat16,pretrained,Original,MistralForCausalLM,14.2153624426921,FALSE,IFEval,0.2266397602805,22.66397602805,BBH,0.451018796279758,23.9508653830296,MATH Level 5,0.0302114803625378,3.02114803625378,GPQA,0.291946308724832,5.59284116331097,MUSR,0.403177083333333,8.36380208333333,MMLU-PRO,0.295295877659575,21.6995419621749,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-22,2024-06-12,0,mistralai/Mistral-7B-v0.3,apache-2.0,406,7.248,0.660475600081291 mistralai/Mistral-Large-Instruct-2411_float16_3a5cb136f6106edf5c1210369068eb5a4f787cab_True,mistralai/Mistral-Large-Instruct-2411,3a5cb136f6106edf5c1210369068eb5a4f787cab,float16,chatmodels,Original,MistralForCausalLM,38.4552314758039,TRUE,IFEval,0.840057713533425,84.0057713533425,BBH,0.674664773567507,52.7448919952634,MATH Level 5,0.0113293051359517,1.13293051359517,GPQA,0.437080536912752,24.9440715883669,MUSR,0.454,17.2166666666667,MMLU-PRO,0.556183510638298,50.6870567375887,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-14,2024-11-19,0,mistralai/Mistral-Large-Instruct-2411,other,167,122.61,26.272305228873 mistralai/Mistral-Nemo-Base-2407_bfloat16_d2efb15544d5401f761235bef327babb850887d0_False,mistralai/Mistral-Nemo-Base-2407,d2efb15544d5401f761235bef327babb850887d0,bfloat16,pretrained,Original,MistralForCausalLM,15.1386511082141,FALSE,IFEval,0.162991972410981,16.2991972410981,BBH,0.503506200036929,29.3747364409669,MATH Level 5,0.0536253776435045,5.36253776435045,GPQA,0.293624161073826,5.8165548098434,MUSR,0.392135416666667,6.51692708333334,MMLU-PRO,0.347157579787234,27.4619533096927,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-18,2024-07-19,0,mistralai/Mistral-Nemo-Base-2407,apache-2.0,263,11.58,1.70299545491031 -mistralai/Mistral-Nemo-Instruct-2407_bfloat16_4d14c1db68fe20dbf80b8eca85d39b909c5fe1d5_True,mistralai/Mistral-Nemo-Instruct-2407,4d14c1db68fe20dbf80b8eca85d39b909c5fe1d5,bfloat16,chatmodels,Original,MistralForCausalLM,23.6333743622513,TRUE,IFEval,0.638024885082692,63.8024885082692,BBH,0.503652395031081,29.6799703811528,MATH Level 5,0.0649546827794562,6.49546827794562,GPQA,0.290268456375839,5.36912751677852,MUSR,0.39,8.48333333333333,MMLU-PRO,0.351728723404255,27.9698581560284,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-17,2024-08-29,1,mistralai/Mistral-Nemo-Base-2407,apache-2.0,1293,12.248,2.99760056248369 -mistralai/Mistral-Small-Instruct-2409_bfloat16_63e53df6575e7085d62113f4383835ff979b3795_True,mistralai/Mistral-Small-Instruct-2409,63e53df6575e7085d62113f4383835ff979b3795,bfloat16,chatmodels,Original,MistralForCausalLM,26.2627489764183,TRUE,IFEval,0.666975846310013,66.6975846310013,BBH,0.521307509814622,30.7920960925092,MATH Level 5,0.143504531722054,14.3504531722054,GPQA,0.323825503355705,9.84340044742729,MUSR,0.363208333333333,3.00104166666667,MMLU-PRO,0.396027260638298,32.8919178486998,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-09-19,0,mistralai/Mistral-Small-Instruct-2409,other,358,22.05,1.37933750885174 -mistralai/Mistral-Small-Instruct-2409_float16_63e53df6575e7085d62113f4383835ff979b3795_False,mistralai/Mistral-Small-Instruct-2409,63e53df6575e7085d62113f4383835ff979b3795,float16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,29.8182425699334,FALSE,IFEval,0.628282955890371,62.8282955890371,BBH,0.583028384689821,40.5597130348992,MATH Level 5,0.197885196374622,19.7885196374622,GPQA,0.333053691275168,11.0738255033557,MUSR,0.406333333333333,10.225,MMLU-PRO,0.409906914893617,34.4341016548463,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-09-25,0,mistralai/Mistral-Small-Instruct-2409,other,358,22.247,1.61000748804136 +mistralai/Mistral-Nemo-Instruct-2407_bfloat16_4d14c1db68fe20dbf80b8eca85d39b909c5fe1d5_True,mistralai/Mistral-Nemo-Instruct-2407,4d14c1db68fe20dbf80b8eca85d39b909c5fe1d5,bfloat16,chatmodels,Original,MistralForCausalLM,23.6333743622513,TRUE,IFEval,0.638024885082692,63.8024885082692,BBH,0.503652395031081,29.6799703811528,MATH Level 5,0.0649546827794562,6.49546827794562,GPQA,0.290268456375839,5.36912751677852,MUSR,0.39,8.48333333333333,MMLU-PRO,0.351728723404255,27.9698581560284,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-17,2024-08-29,1,mistralai/Mistral-Nemo-Base-2407,apache-2.0,1295,12.248,2.99760056248369 +mistralai/Mistral-Small-Instruct-2409_bfloat16_63e53df6575e7085d62113f4383835ff979b3795_True,mistralai/Mistral-Small-Instruct-2409,63e53df6575e7085d62113f4383835ff979b3795,bfloat16,chatmodels,Original,MistralForCausalLM,26.2627489764183,TRUE,IFEval,0.666975846310013,66.6975846310013,BBH,0.521307509814622,30.7920960925092,MATH Level 5,0.143504531722054,14.3504531722054,GPQA,0.323825503355705,9.84340044742729,MUSR,0.363208333333333,3.00104166666667,MMLU-PRO,0.396027260638298,32.8919178486998,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-09-19,0,mistralai/Mistral-Small-Instruct-2409,other,357,22.05,1.37933750885174 +mistralai/Mistral-Small-Instruct-2409_float16_63e53df6575e7085d62113f4383835ff979b3795_False,mistralai/Mistral-Small-Instruct-2409,63e53df6575e7085d62113f4383835ff979b3795,float16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,29.8182425699334,FALSE,IFEval,0.628282955890371,62.8282955890371,BBH,0.583028384689821,40.5597130348992,MATH Level 5,0.197885196374622,19.7885196374622,GPQA,0.333053691275168,11.0738255033557,MUSR,0.406333333333333,10.225,MMLU-PRO,0.409906914893617,34.4341016548463,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-17,2024-09-25,0,mistralai/Mistral-Small-Instruct-2409,other,357,22.247,1.61000748804136 mistralai/Mixtral-8x22B-Instruct-v0.1_bfloat16_b0c3516041d014f640267b14feb4e9a84c8e8c71_True,mistralai/Mixtral-8x22B-Instruct-v0.1,b0c3516041d014f640267b14feb4e9a84c8e8c71,bfloat16,chatmodels,Original,MixtralForCausalLM,33.885680288082,TRUE,IFEval,0.718358400156031,71.8358400156031,BBH,0.612492492627202,44.1143455872484,MATH Level 5,0.187311178247734,18.7311178247734,GPQA,0.373322147651007,16.4429530201342,MUSR,0.431114583333333,13.4893229166667,MMLU-PRO,0.448304521276596,38.7005023640662,TRUE,FALSE,TRUE,FALSE,TRUE,2024-04-16,2024-06-12,1,mistralai/Mixtral-8x22B-v0.1,apache-2.0,695,140.621,47.147578592378 mistralai/Mixtral-8x22B-v0.1_bfloat16_b03e260818710044a2f088d88fab12bb220884fb_False,mistralai/Mixtral-8x22B-v0.1,b03e260818710044a2f088d88fab12bb220884fb,bfloat16,pretrained,Original,MixtralForCausalLM,25.7283481584049,FALSE,IFEval,0.258263629392235,25.8263629392235,BBH,0.623980747318727,45.5884038434272,MATH Level 5,0.182779456193354,18.2779456193354,GPQA,0.375838926174497,16.7785234899329,MUSR,0.403697916666667,7.46223958333334,MMLU-PRO,0.463929521276596,40.4366134751773,TRUE,FALSE,TRUE,FALSE,TRUE,2024-04-16,2024-06-12,0,mistralai/Mixtral-8x22B-v0.1,apache-2.0,201,140.621,104.697316275112 mistralai/Mixtral-8x7B-Instruct-v0.1_bfloat16_1e637f2d7cb0a9d6fb1922f305cb784995190a83_True,mistralai/Mixtral-8x7B-Instruct-v0.1,1e637f2d7cb0a9d6fb1922f305cb784995190a83,bfloat16,chatmodels,Original,MixtralForCausalLM,23.8422789394817,TRUE,IFEval,0.559914360563305,55.9914360563305,BBH,0.496236540133565,29.7423983809673,MATH Level 5,0.0929003021148036,9.29003021148036,GPQA,0.302852348993289,7.04697986577182,MUSR,0.420322916666667,11.0736979166667,MMLU-PRO,0.369182180851064,29.9091312056738,TRUE,FALSE,TRUE,FALSE,TRUE,2023-12-10,2024-06-12,1,mistralai/Mixtral-8x7B-v0.1,apache-2.0,4223,46.703,13.7649393661468 @@ -1700,9 +1700,9 @@ nbeerbower/Llama-3.1-Nemotron-lorablated-70B_bfloat16_f335a582cdb7fb0e63a7343a90 nbeerbower/Llama3.1-Gutenberg-Doppel-70B_bfloat16_5de156e97f776ce1b88ce5b2e2dc1e7709205a82_True,nbeerbower/Llama3.1-Gutenberg-Doppel-70B,5de156e97f776ce1b88ce5b2e2dc1e7709205a82,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,35.803047625424,TRUE,IFEval,0.709215991347403,70.9215991347403,BBH,0.666089125599447,52.5567789951991,MATH Level 5,0.145015105740181,14.5015105740181,GPQA,0.344798657718121,12.6398210290828,MUSR,0.48971875,22.6815104166667,MMLU-PRO,0.473653590425532,41.5170656028369,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-11,2024-10-12,1,nbeerbower/Llama3.1-Gutenberg-Doppel-70B (Merge),llama3.1,5,70.554,9.99359303531585 nbeerbower/Lyra-Gutenberg-mistral-nemo-12B_bfloat16_5c506391eb02075e02f4cf5953b443505d646bce_True,nbeerbower/Lyra-Gutenberg-mistral-nemo-12B,5c506391eb02075e02f4cf5953b443505d646bce,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,22.7037183339816,TRUE,IFEval,0.34948824674087,34.948824674087,BBH,0.558624574155575,36.9924324393759,MATH Level 5,0.0913897280966767,9.13897280966767,GPQA,0.333892617449664,11.1856823266219,MUSR,0.435666666666667,14.7583333333333,MMLU-PRO,0.362782579787234,29.1980644208038,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-23,2024-09-03,1,nbeerbower/Lyra-Gutenberg-mistral-nemo-12B (Merge),cc-by-nc-4.0,17,12.248,1.91860194008568 nbeerbower/Lyra4-Gutenberg-12B_bfloat16_cb6911be3475da99a810071c04803d6edfb5965b_False,nbeerbower/Lyra4-Gutenberg-12B,cb6911be3475da99a810071c04803d6edfb5965b,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,19.8189429963454,FALSE,IFEval,0.221218588899675,22.1218588899675,BBH,0.538669487933139,34.2355927548016,MATH Level 5,0.128398791540786,12.8398791540786,GPQA,0.318791946308725,9.17225950782998,MUSR,0.403791666666667,11.9739583333333,MMLU-PRO,0.357130984042553,28.5701093380615,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-09,2024-09-12,1,nbeerbower/Lyra4-Gutenberg-12B (Merge),cc-by-nc-4.0,19,12.248,1.69053358579243 -nbeerbower/Lyra4-Gutenberg2-12B_bfloat16_6a5f117695cc729de16da87654b979e6df72ed2f_False,nbeerbower/Lyra4-Gutenberg2-12B,6a5f117695cc729de16da87654b979e6df72ed2f,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,19.9322936794633,FALSE,IFEval,0.258512967814288,25.8512967814288,BBH,0.534452794475004,33.7306396244006,MATH Level 5,0.11631419939577,11.631419939577,GPQA,0.312919463087248,8.38926174496644,MUSR,0.39721875,11.4856770833333,MMLU-PRO,0.35654920212766,28.5054669030733,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-29,2024-10-01,1,nbeerbower/Lyra4-Gutenberg2-12B (Merge),cc-by-nc-4.0,8,12.248,1.80933957140369 +nbeerbower/Lyra4-Gutenberg2-12B_bfloat16_6a5f117695cc729de16da87654b979e6df72ed2f_False,nbeerbower/Lyra4-Gutenberg2-12B,6a5f117695cc729de16da87654b979e6df72ed2f,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,19.9322936794633,FALSE,IFEval,0.258512967814288,25.8512967814288,BBH,0.534452794475004,33.7306396244006,MATH Level 5,0.11631419939577,11.631419939577,GPQA,0.312919463087248,8.38926174496644,MUSR,0.39721875,11.4856770833333,MMLU-PRO,0.35654920212766,28.5054669030733,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-29,2024-10-01,1,nbeerbower/Lyra4-Gutenberg2-12B (Merge),cc-by-nc-4.0,9,12.248,1.80933957140369 nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated_bfloat16_8c9eecaace50659647c7d8b569237ad068a6c837_True,nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated,8c9eecaace50659647c7d8b569237ad068a6c837,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,26.534810293518,TRUE,IFEval,0.682488020674034,68.2488020674034,BBH,0.549604038007944,36.0773810041614,MATH Level 5,0.0581570996978852,5.81570996978852,GPQA,0.279362416107383,3.91498881431767,MUSR,0.452166666666667,16.5541666666667,MMLU-PRO,0.357380319148936,28.5978132387707,TRUE,TRUE,FALSE,FALSE,FALSE,2024-10-19,2024-10-19,1,nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated (Merge),apache-2.0,2,12.248,1.40542449542991 -nbeerbower/Mistral-Gutenberg-Doppel-7B-FFT_bfloat16_5735876465b6f2523fdedb73120c3f97d04556d3_True,nbeerbower/Mistral-Gutenberg-Doppel-7B-FFT,5735876465b6f2523fdedb73120c3f97d04556d3,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,18.3382757286568,TRUE,IFEval,0.571679809571936,57.1679809571936,BBH,0.407625408902559,17.3465749558437,MATH Level 5,0.0249244712990937,2.49244712990937,GPQA,0.283557046979866,4.47427293064877,MUSR,0.4059375,9.3421875,MMLU-PRO,0.272855718085106,19.2061908983452,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-18,2024-11-18,1,nbeerbower/Mistral-Gutenberg-Doppel-7B-FFT (Merge),apache-2.0,1,7.242,0.436816283436552 +nbeerbower/Mistral-Gutenberg-Doppel-7B-FFT_bfloat16_5735876465b6f2523fdedb73120c3f97d04556d3_True,nbeerbower/Mistral-Gutenberg-Doppel-7B-FFT,5735876465b6f2523fdedb73120c3f97d04556d3,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,18.3382757286568,TRUE,IFEval,0.571679809571936,57.1679809571936,BBH,0.407625408902559,17.3465749558437,MATH Level 5,0.0249244712990937,2.49244712990937,GPQA,0.283557046979866,4.47427293064877,MUSR,0.4059375,9.3421875,MMLU-PRO,0.272855718085106,19.2061908983452,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-18,2024-11-18,1,nbeerbower/Mistral-Gutenberg-Doppel-7B-FFT (Merge),apache-2.0,2,7.242,0.436816283436552 nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B_bfloat16_0eaaac89d4b53e94d5b78220b24439a026ee29e6_False,nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B,0eaaac89d4b53e94d5b78220b24439a026ee29e6,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,21.4750463954239,FALSE,IFEval,0.356706871102009,35.6706871102009,BBH,0.52746069994735,32.4215267593987,MATH Level 5,0.117824773413897,11.7824773413897,GPQA,0.316275167785235,8.83668903803132,MUSR,0.41321875,11.4856770833333,MMLU-PRO,0.357878989361702,28.6532210401891,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-26,2024-09-26,1,nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B (Merge),apache-2.0,3,12.248,1.77677129514725 nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2_bfloat16_adc1ccd9d83d24e41bed895f989803af87ea2d2c_True,nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2,adc1ccd9d83d24e41bed895f989803af87ea2d2c,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,24.7179805965211,TRUE,IFEval,0.653586927131123,65.3586927131123,BBH,0.537449617223581,34.3574128499151,MATH Level 5,0.0445619335347432,4.45619335347432,GPQA,0.270973154362416,2.79642058165548,MUSR,0.423302083333333,13.04609375,MMLU-PRO,0.354637632978723,28.2930703309693,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-04,2024-10-09,1,nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2 (Merge),apache-2.0,7,12.248,1.40485653342015 nbeerbower/Mistral-Nemo-Moderne-12B-FFT-experimental_bfloat16_e52f7b7c3ade2a6212f29dd1054332cee21ab85d_True,nbeerbower/Mistral-Nemo-Moderne-12B-FFT-experimental,e52f7b7c3ade2a6212f29dd1054332cee21ab85d,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,17.1753567408191,TRUE,IFEval,0.335224980828646,33.5224980828646,BBH,0.523408917923726,32.0715397550976,MATH Level 5,0.020392749244713,2.0392749244713,GPQA,0.281040268456376,4.13870246085012,MUSR,0.371489583333333,4.00286458333333,MMLU-PRO,0.345495345744681,27.2772606382979,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-19,2024-11-26,1,nbeerbower/Mistral-Nemo-Moderne-12B-FFT-experimental (Merge),apache-2.0,1,12.248,1.21715741422502 @@ -1715,17 +1715,17 @@ nbeerbower/Nemo-Loony-12B-experimental_bfloat16_7b06f30502a9b58c028ac1079e1b3d29 nbeerbower/Qwen2.5-Gutenberg-Doppel-14B_bfloat16_11a5060f9e7315ea07241106f086ac4694dded60_True,nbeerbower/Qwen2.5-Gutenberg-Doppel-14B,11a5060f9e7315ea07241106f086ac4694dded60,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,32.3021151341188,TRUE,IFEval,0.809083232489794,80.9083232489794,BBH,0.638173575518332,48.2389086303922,MATH Level 5,0,0,GPQA,0.333053691275168,11.0738255033557,MUSR,0.4100625,10.0244791666667,MMLU-PRO,0.492104388297872,43.5671542553192,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-11,2024-11-11,1,nbeerbower/Qwen2.5-Gutenberg-Doppel-14B (Merge),apache-2.0,11,14.77,1.69061186545046 nbeerbower/SmolNemo-12B-FFT-experimental_bfloat16_d8d7a90ae9b9cb79cdc0912a685c3cb8d7a25560_True,nbeerbower/SmolNemo-12B-FFT-experimental,d8d7a90ae9b9cb79cdc0912a685c3cb8d7a25560,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,8.32005450172091,TRUE,IFEval,0.334800551425773,33.4800551425773,BBH,0.333608881049446,6.54243853417972,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.26006711409396,1.34228187919463,MUSR,0.384697916666667,5.92057291666667,MMLU-PRO,0.121675531914894,2.40839243498818,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-25,2024-11-26,1,nbeerbower/SmolNemo-12B-FFT-experimental (Merge),apache-2.0,0,12.248,1.22541475582758 nbeerbower/Stella-mistral-nemo-12B-v2_bfloat16_b81bab28f7dcb25a0aa0fe4dcf957f3083ee6b43_False,nbeerbower/Stella-mistral-nemo-12B-v2,b81bab28f7dcb25a0aa0fe4dcf957f3083ee6b43,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,22.4303691339052,FALSE,IFEval,0.327431215840636,32.7431215840636,BBH,0.548375095649521,35.3645161006864,MATH Level 5,0.112537764350453,11.2537764350453,GPQA,0.332214765100671,10.9619686800895,MUSR,0.430395833333333,14.4328125,MMLU-PRO,0.368434175531915,29.8260195035461,FALSE,FALSE,FALSE,FALSE,FALSE,2024-09-07,2024-09-14,1,nbeerbower/Stella-mistral-nemo-12B-v2 (Merge),"",3,12.248,1.74087209150781 -nbeerbower/gemma2-gutenberg-27B_bfloat16_d4febe52e8b7b13a98126dbf1716ed1329f48922_False,nbeerbower/gemma2-gutenberg-27B,d4febe52e8b7b13a98126dbf1716ed1329f48922,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,10.1089609543278,FALSE,IFEval,0.294708041330337,29.4708041330337,BBH,0.379656835034516,13.0915249120265,MATH Level 5,0,0,GPQA,0.272651006711409,3.02013422818792,MUSR,0.372729166666667,4.1578125,MMLU-PRO,0.198221409574468,10.9134899527187,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-09,2024-09-23,1,nbeerbower/gemma2-gutenberg-27B (Merge),gemma,4,27.227,7.69545826973842 +nbeerbower/gemma2-gutenberg-27B_bfloat16_d4febe52e8b7b13a98126dbf1716ed1329f48922_False,nbeerbower/gemma2-gutenberg-27B,d4febe52e8b7b13a98126dbf1716ed1329f48922,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,10.1089609543278,FALSE,IFEval,0.294708041330337,29.4708041330337,BBH,0.379656835034516,13.0915249120265,MATH Level 5,0,0,GPQA,0.272651006711409,3.02013422818792,MUSR,0.372729166666667,4.1578125,MMLU-PRO,0.198221409574468,10.9134899527187,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-09,2024-09-23,1,nbeerbower/gemma2-gutenberg-27B (Merge),gemma,5,27.227,7.69545826973842 nbeerbower/gemma2-gutenberg-9B_bfloat16_ebdab2d41f257fc9e7c858498653644d13386ce5_False,nbeerbower/gemma2-gutenberg-9B,ebdab2d41f257fc9e7c858498653644d13386ce5,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,22.6492565233012,FALSE,IFEval,0.279594808441602,27.9594808441602,BBH,0.595090400149033,42.3556110680972,MATH Level 5,0.0166163141993958,1.66163141993958,GPQA,0.338087248322148,11.744966442953,MUSR,0.459510416666667,16.70546875,MMLU-PRO,0.419215425531915,35.4683806146572,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-14,2024-08-03,1,nbeerbower/gemma2-gutenberg-9B (Merge),gemma,12,9.242,2.80960876884905 -nbeerbower/llama-3-gutenberg-8B_bfloat16_4ed3aac5e30c078bee79ae193c2d301d38860b20_False,nbeerbower/llama-3-gutenberg-8B,4ed3aac5e30c078bee79ae193c2d301d38860b20,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,21.2962289397565,FALSE,IFEval,0.437191097399345,43.7191097399345,BBH,0.499360025619942,27.9581327241913,MATH Level 5,0.0777945619335348,7.77945619335348,GPQA,0.301174496644295,6.82326621923937,MUSR,0.407302083333333,10.04609375,MMLU-PRO,0.383061835106383,31.4513150118203,TRUE,FALSE,FALSE,FALSE,FALSE,2024-05-05,2024-07-10,1,nbeerbower/llama-3-gutenberg-8B (Merge),other,7,8.03,0.883569390504619 +nbeerbower/llama-3-gutenberg-8B_bfloat16_4ed3aac5e30c078bee79ae193c2d301d38860b20_False,nbeerbower/llama-3-gutenberg-8B,4ed3aac5e30c078bee79ae193c2d301d38860b20,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,21.2962289397565,FALSE,IFEval,0.437191097399345,43.7191097399345,BBH,0.499360025619942,27.9581327241913,MATH Level 5,0.0777945619335348,7.77945619335348,GPQA,0.301174496644295,6.82326621923937,MUSR,0.407302083333333,10.04609375,MMLU-PRO,0.383061835106383,31.4513150118203,TRUE,FALSE,FALSE,FALSE,FALSE,2024-05-05,2024-07-10,1,nbeerbower/llama-3-gutenberg-8B (Merge),other,8,8.03,0.883569390504619 nbeerbower/llama3.1-cc-8B_bfloat16_5269bb26f1afe005f144564f484e7554f185239f_False,nbeerbower/llama3.1-cc-8B,5269bb26f1afe005f144564f484e7554f185239f,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,20.2560416607539,FALSE,IFEval,0.506808601178207,50.6808601178207,BBH,0.487118742861439,26.4838116934266,MATH Level 5,0.0709969788519638,7.09969788519638,GPQA,0.285234899328859,4.6979865771812,MUSR,0.388510416666667,6.49713541666667,MMLU-PRO,0.334690824468085,26.0767582742317,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-18,2024-09-14,1,nbeerbower/llama3.1-cc-8B (Merge),llama3,1,8.03,0.937237460746167 nbeerbower/mistral-nemo-bophades-12B_bfloat16_252a358e099f77a0a28125e00a57aa3a107b3910_True,nbeerbower/mistral-nemo-bophades-12B,252a358e099f77a0a28125e00a57aa3a107b3910,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,24.847434103672,TRUE,IFEval,0.679440551071158,67.9440551071158,BBH,0.498847151585388,29.543905352145,MATH Level 5,0.0702416918429003,7.02416918429003,GPQA,0.285234899328859,4.6979865771812,MUSR,0.41778125,12.0893229166667,MMLU-PRO,0.350066489361702,27.7851654846336,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-13,2024-09-03,1,nbeerbower/mistral-nemo-bophades-12B (Merge),apache-2.0,8,12.248,2.0523465046134 nbeerbower/mistral-nemo-cc-12B_bfloat16_fc32293e0b022d6daef9bfdb0c54d57a5226bf9a_False,nbeerbower/mistral-nemo-cc-12B,fc32293e0b022d6daef9bfdb0c54d57a5226bf9a,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,17.0775291049971,FALSE,IFEval,0.143532493783162,14.3532493783162,BBH,0.539940954648752,34.4465470195227,MATH Level 5,0.0181268882175227,1.81268882175227,GPQA,0.315436241610738,8.7248322147651,MUSR,0.442364583333333,14.2622395833333,MMLU-PRO,0.359790558510638,28.8656176122931,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-18,2024-09-14,1,nbeerbower/mistral-nemo-cc-12B (Merge),apache-2.0,1,12.248,1.49462242080501 nbeerbower/mistral-nemo-gutades-12B_bfloat16_5689f929808a6165f94ba43f872b944a4bdaaea3_False,nbeerbower/mistral-nemo-gutades-12B,5689f929808a6165f94ba43f872b944a4bdaaea3,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,21.0003959585461,FALSE,IFEval,0.342518960801784,34.2518960801784,BBH,0.540719425968437,34.5744082187269,MATH Level 5,0.113293051359517,11.3293051359517,GPQA,0.315436241610738,8.7248322147651,MUSR,0.404041666666667,8.671875,MMLU-PRO,0.356050531914894,28.4500591016548,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-17,2024-09-23,1,nbeerbower/mistral-nemo-gutades-12B (Merge),apache-2.0,2,12.248,1.82462005600131 nbeerbower/mistral-nemo-gutenberg-12B_bfloat16_6aeb6f769a53eb111839db8f439b614730e39593_False,nbeerbower/mistral-nemo-gutenberg-12B,6aeb6f769a53eb111839db8f439b614730e39593,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,20.998978731179,FALSE,IFEval,0.350386973231027,35.0386973231027,BBH,0.528136370769781,32.4338743419766,MATH Level 5,0.114803625377644,11.4803625377644,GPQA,0.307046979865772,7.60626398210291,MUSR,0.4170625,10.9661458333333,MMLU-PRO,0.356216755319149,28.4685283687943,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-12,2024-09-03,1,nbeerbower/mistral-nemo-gutenberg-12B (Merge),apache-2.0,7,12.248,1.57481457024687 -nbeerbower/mistral-nemo-gutenberg-12B-v2_bfloat16_86bf9c105ff40835132e41699ac1a76ee0e5b683_True,nbeerbower/mistral-nemo-gutenberg-12B-v2,86bf9c105ff40835132e41699ac1a76ee0e5b683,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,24.1170388704527,TRUE,IFEval,0.620339587849129,62.0339587849129,BBH,0.539720378828347,34.7306163392809,MATH Level 5,0.0249244712990937,2.49244712990937,GPQA,0.277684563758389,3.69127516778523,MUSR,0.428697916666667,13.9872395833333,MMLU-PRO,0.349900265957447,27.7666962174941,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-13,2024-09-03,1,nbeerbower/mistral-nemo-gutenberg-12B-v2 (Merge),apache-2.0,26,12.248,2.87090780218261 -nbeerbower/mistral-nemo-gutenberg-12B-v3_bfloat16_3e1a716281f23280abd72e402139c578faca175a_False,nbeerbower/mistral-nemo-gutenberg-12B-v3,3e1a716281f23280abd72e402139c578faca175a,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,19.1772190822211,FALSE,IFEval,0.218270854665621,21.8270854665621,BBH,0.544065799051091,34.9579145629564,MATH Level 5,0.0528700906344411,5.28700906344411,GPQA,0.314597315436242,8.61297539149888,MUSR,0.44503125,14.9955729166667,MMLU-PRO,0.364444813829787,29.3827570921986,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-15,2024-09-03,1,nbeerbower/mistral-nemo-gutenberg-12B-v3 (Merge),apache-2.0,10,12.248,1.83536904886502 -nbeerbower/mistral-nemo-gutenberg-12B-v4_bfloat16_59409afe585ae6945a588c867f879a9d31e571e6_False,nbeerbower/mistral-nemo-gutenberg-12B-v4,59409afe585ae6945a588c867f879a9d31e571e6,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,19.7508646303857,FALSE,IFEval,0.237929804031082,23.7929804031082,BBH,0.526902886482367,31.9712582735826,MATH Level 5,0.120845921450151,12.0845921450151,GPQA,0.316275167785235,8.83668903803132,MUSR,0.410427083333333,13.2033854166667,MMLU-PRO,0.357546542553192,28.6162825059102,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-22,2024-09-03,1,nbeerbower/mistral-nemo-gutenberg-12B-v4 (Merge),apache-2.0,17,12.248,1.7604613367812 +nbeerbower/mistral-nemo-gutenberg-12B-v2_bfloat16_86bf9c105ff40835132e41699ac1a76ee0e5b683_True,nbeerbower/mistral-nemo-gutenberg-12B-v2,86bf9c105ff40835132e41699ac1a76ee0e5b683,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,24.1170388704527,TRUE,IFEval,0.620339587849129,62.0339587849129,BBH,0.539720378828347,34.7306163392809,MATH Level 5,0.0249244712990937,2.49244712990937,GPQA,0.277684563758389,3.69127516778523,MUSR,0.428697916666667,13.9872395833333,MMLU-PRO,0.349900265957447,27.7666962174941,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-13,2024-09-03,1,nbeerbower/mistral-nemo-gutenberg-12B-v2 (Merge),apache-2.0,27,12.248,2.87090780218261 +nbeerbower/mistral-nemo-gutenberg-12B-v3_bfloat16_3e1a716281f23280abd72e402139c578faca175a_False,nbeerbower/mistral-nemo-gutenberg-12B-v3,3e1a716281f23280abd72e402139c578faca175a,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,19.1772190822211,FALSE,IFEval,0.218270854665621,21.8270854665621,BBH,0.544065799051091,34.9579145629564,MATH Level 5,0.0528700906344411,5.28700906344411,GPQA,0.314597315436242,8.61297539149888,MUSR,0.44503125,14.9955729166667,MMLU-PRO,0.364444813829787,29.3827570921986,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-15,2024-09-03,1,nbeerbower/mistral-nemo-gutenberg-12B-v3 (Merge),apache-2.0,11,12.248,1.83536904886502 +nbeerbower/mistral-nemo-gutenberg-12B-v4_bfloat16_59409afe585ae6945a588c867f879a9d31e571e6_False,nbeerbower/mistral-nemo-gutenberg-12B-v4,59409afe585ae6945a588c867f879a9d31e571e6,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,19.7508646303857,FALSE,IFEval,0.237929804031082,23.7929804031082,BBH,0.526902886482367,31.9712582735826,MATH Level 5,0.120845921450151,12.0845921450151,GPQA,0.316275167785235,8.83668903803132,MUSR,0.410427083333333,13.2033854166667,MMLU-PRO,0.357546542553192,28.6162825059102,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-22,2024-09-03,1,nbeerbower/mistral-nemo-gutenberg-12B-v4 (Merge),apache-2.0,18,12.248,1.7604613367812 nbeerbower/mistral-nemo-gutenberg2-12B-test_bfloat16_10da6150b0bedf8fd59206d72c4c0335ac665df3_False,nbeerbower/mistral-nemo-gutenberg2-12B-test,10da6150b0bedf8fd59206d72c4c0335ac665df3,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,20.9202274833549,FALSE,IFEval,0.338471921169164,33.8471921169164,BBH,0.525477908630255,32.0447592859638,MATH Level 5,0.113293051359517,11.3293051359517,GPQA,0.317114093959732,8.94854586129754,MUSR,0.415729166666667,10.9661458333333,MMLU-PRO,0.35546875,28.3854166666667,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-24,2024-09-25,1,nbeerbower/mistral-nemo-gutenberg2-12B-test (Merge),apache-2.0,1,12.248,1.67502697085804 nbeerbower/mistral-nemo-wissenschaft-12B_bfloat16_2480f9924415c72fe00ae9391bb15a6d05c889eb_True,nbeerbower/mistral-nemo-wissenschaft-12B,2480f9924415c72fe00ae9391bb15a6d05c889eb,bfloat16,chatmodels,Original,MistralForCausalLM,24.6791101549788,TRUE,IFEval,0.652013324645275,65.2013324645275,BBH,0.504030612099318,29.5679994157152,MATH Level 5,0.0717522658610272,7.17522658610272,GPQA,0.292785234899329,5.70469798657718,MUSR,0.41778125,12.2893229166667,MMLU-PRO,0.353224734042553,28.1360815602837,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-12,2024-08-30,1,nbeerbower/mistral-nemo-wissenschaft-12B (Merge),apache-2.0,6,12.248,1.42937341944478 nbrahme/IndusQ_bfloat16_d4224f753e6a2d6e7476752fb927c26c55ec9467_True,nbrahme/IndusQ,d4224f753e6a2d6e7476752fb927c26c55ec9467,bfloat16,fine-tunedondomain-specificdatasets,Original,GPT2LMHeadModel,5.62354592681778,TRUE,IFEval,0.243974875552423,24.3974875552423,BBH,0.30624035198475,3.74709649597406,MATH Level 5,0,0,GPQA,0.26510067114094,2.01342281879195,MUSR,0.336635416666667,2.24609375,MMLU-PRO,0.112034574468085,1.33717494089835,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-09-18,0,Removed,"",0,1.176,0.15061686517706 @@ -1775,13 +1775,13 @@ nlpguy/Mistral-NeMo-Minitron-Upscale-v2_bfloat16_4ac077e496705687fdcbe51f3b915be nlpguy/Mistral-NeMo-Minitron-Upscale-v3_bfloat16_6703b09d3d78cc020448ee93c53dc727312bcbaf_False,nlpguy/Mistral-NeMo-Minitron-Upscale-v3,6703b09d3d78cc020448ee93c53dc727312bcbaf,bfloat16,pretrained,Original,MistralForCausalLM,5.01343743805603,FALSE,IFEval,0.141209767860388,14.1209767860388,BBH,0.305245226029181,3.39826644771649,MATH Level 5,0,0,GPQA,0.259228187919463,1.23042505592841,MUSR,0.40984375,9.43046875,MMLU-PRO,0.117104388297872,1.90048758865248,TRUE,TRUE,FALSE,FALSE,FALSE,2024-10-04,2024-10-04,1,nlpguy/Mistral-NeMo-Minitron-Upscale-v3 (Merge),other,1,12.451,6.04466857955523 nlpguy/StableProse_bfloat16_4937dc747684705e4b87df27b47eab5429f3a9c1_False,nlpguy/StableProse,4937dc747684705e4b87df27b47eab5429f3a9c1,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,16.4224949318479,FALSE,IFEval,0.197238881722718,19.7238881722718,BBH,0.511655862557709,30.180202714186,MATH Level 5,0.0528700906344411,5.28700906344411,GPQA,0.302852348993289,7.04697986577182,MUSR,0.406708333333333,8.871875,MMLU-PRO,0.346825132978723,27.4250147754137,FALSE,FALSE,FALSE,FALSE,FALSE,2024-08-16,2024-08-17,1,nlpguy/StableProse (Merge),"",1,12.248,1.79436305574144 nlpguy/StarFusion-alpha1_bfloat16_dccad965a710d7bee001b6387c8307e7c320291e_True,nlpguy/StarFusion-alpha1,dccad965a710d7bee001b6387c8307e7c320291e,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,20.8409116698443,TRUE,IFEval,0.566009299769057,56.6009299769057,BBH,0.442869411550703,21.9331816356547,MATH Level 5,0.0725075528700906,7.25075528700906,GPQA,0.295302013422819,6.04026845637584,MUSR,0.408104166666667,8.8796875,MMLU-PRO,0.319065824468085,24.3406471631206,TRUE,TRUE,FALSE,FALSE,FALSE,2024-04-13,2024-06-26,1,nlpguy/StarFusion-alpha1 (Merge),apache-2.0,0,7.242,1.17440574036271 -nothingiisreal/L3.1-8B-Celeste-V1.5_bfloat16_e7ea0e3d2727c8cf66c0481ffa251f28cb85429f_True,nothingiisreal/L3.1-8B-Celeste-V1.5,e7ea0e3d2727c8cf66c0481ffa251f28cb85429f,bfloat16,chatmodels,Original,LlamaForCausalLM,26.1217933643791,TRUE,IFEval,0.732671533752665,73.2671533752665,BBH,0.501179682272114,28.8879669256676,MATH Level 5,0.143504531722054,14.3504531722054,GPQA,0.284395973154362,4.58612975391499,MUSR,0.374864583333333,5.59140625,MMLU-PRO,0.370428856382979,30.0476507092199,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-27,2024-12-04,0,nothingiisreal/L3.1-8B-Celeste-V1.5,llama3.1,36,8.03,0.707164119253143 +nothingiisreal/L3.1-8B-Celeste-V1.5_bfloat16_e7ea0e3d2727c8cf66c0481ffa251f28cb85429f_True,nothingiisreal/L3.1-8B-Celeste-V1.5,e7ea0e3d2727c8cf66c0481ffa251f28cb85429f,bfloat16,chatmodels,Original,LlamaForCausalLM,26.1217933643791,TRUE,IFEval,0.732671533752665,73.2671533752665,BBH,0.501179682272114,28.8879669256676,MATH Level 5,0.143504531722054,14.3504531722054,GPQA,0.284395973154362,4.58612975391499,MUSR,0.374864583333333,5.59140625,MMLU-PRO,0.370428856382979,30.0476507092199,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-27,2024-12-04,0,nothingiisreal/L3.1-8B-Celeste-V1.5,llama3.1,37,8.03,0.707164119253143 nothingiisreal/MN-12B-Starcannon-v2_bfloat16_f2ff756e8c32d9107d4f6a3c18c730e3fe0cae88_True,nothingiisreal/MN-12B-Starcannon-v2,f2ff756e8c32d9107d4f6a3c18c730e3fe0cae88,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,18.0303925028944,TRUE,IFEval,0.392527382899595,39.2527382899595,BBH,0.500449988847177,28.4247829635739,MATH Level 5,0.0506042296072508,5.06042296072508,GPQA,0.278523489932886,3.80313199105145,MUSR,0.3978125,7.99322916666667,MMLU-PRO,0.312832446808511,23.6480496453901,TRUE,TRUE,FALSE,FALSE,FALSE,2024-08-13,2024-09-03,1,nothingiisreal/MN-12B-Starcannon-v2 (Merge),apache-2.0,6,12.248,1.72266278455511 nothingiisreal/MN-12B-Starcannon-v3_bfloat16_169480b62121c4f070e93a05158545c679712644_True,nothingiisreal/MN-12B-Starcannon-v3,169480b62121c4f070e93a05158545c679712644,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,18.993413862427,TRUE,IFEval,0.380737554134142,38.0737554134142,BBH,0.517055344479572,30.8730016263886,MATH Level 5,0.0687311178247734,6.87311178247734,GPQA,0.273489932885906,3.13199105145414,MUSR,0.404635416666667,9.84609375,MMLU-PRO,0.326462765957447,25.1625295508274,FALSE,FALSE,FALSE,FALSE,FALSE,2024-08-13,2024-09-03,1,nothingiisreal/MN-12B-Starcannon-v3 (Merge),"",11,12.248,1.74567093087938 nvidia/Hymba-1.5B-Base_bfloat16_85e5b833d75f26170c7684ba83140f1bf9fedf37_False,nvidia/Hymba-1.5B-Base,85e5b833d75f26170c7684ba83140f1bf9fedf37,bfloat16,pretrained,Original,HymbaForCausalLM,7.92198908307419,FALSE,IFEval,0.229512138902556,22.9512138902556,BBH,0.325647852141822,7.68994111813814,MATH Level 5,0.006797583081571,0.6797583081571,GPQA,0.255872483221477,0.782997762863532,MUSR,0.356635416666667,5.17942708333334,MMLU-PRO,0.192237367021277,10.2485963356974,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-09,2024-12-06,0,nvidia/Hymba-1.5B-Base,other,125,1.523,9.10791437880169 nvidia/Hymba-1.5B-Instruct_bfloat16_ffc758eefef247c0ee4d7ce41636562759027ce6_True,nvidia/Hymba-1.5B-Instruct,ffc758eefef247c0ee4d7ce41636562759027ce6,bfloat16,chatmodels,Original,HymbaForCausalLM,13.7392113616459,TRUE,IFEval,0.600905597148898,60.0905597148898,BBH,0.306713390823188,4.59146361547248,MATH Level 5,0,0,GPQA,0.288590604026846,5.14541387024609,MUSR,0.331583333333333,1.04791666666667,MMLU-PRO,0.204039228723404,11.5599143026005,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-31,2024-12-06,1,nvidia/Hymba-1.5B-Instruct (Merge),other,204,1.523,6.71266576424283 nvidia/Llama-3.1-Minitron-4B-Depth-Base_bfloat16_40d82bc951b4f39e9c9e11176334250c30975098_False,nvidia/Llama-3.1-Minitron-4B-Depth-Base,40d82bc951b4f39e9c9e11176334250c30975098,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,11.5321699752737,FALSE,IFEval,0.16069362624503,16.069362624503,BBH,0.417070419310489,19.4441095555079,MATH Level 5,0.0120845921450151,1.20845921450151,GPQA,0.263422818791946,1.78970917225951,MUSR,0.4010625,10.6994791666667,MMLU-PRO,0.27983710106383,19.9819001182033,TRUE,FALSE,FALSE,FALSE,TRUE,2024-08-13,2024-09-25,0,nvidia/Llama-3.1-Minitron-4B-Depth-Base,other,20,4.02,0.467690635805229 -nvidia/Llama-3.1-Nemotron-70B-Instruct-HF_bfloat16_250db5cf2323e04a6d2025a2ca2b94a95c439e88_True,nvidia/Llama-3.1-Nemotron-70B-Instruct-HF,250db5cf2323e04a6d2025a2ca2b94a95c439e88,bfloat16,chatmodels,Original,LlamaForCausalLM,34.5783715382223,TRUE,IFEval,0.738067217205903,73.8067217205903,BBH,0.631600066889504,47.1095304937273,MATH Level 5,0.287009063444109,28.7009063444109,GPQA,0.258389261744966,1.11856823266219,MUSR,0.432760416666667,13.1950520833333,MMLU-PRO,0.491855053191489,43.5394503546099,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-12,2024-10-16,2,meta-llama/Meta-Llama-3.1-70B,llama3.1,1861,70.554,13.6287476336013 +nvidia/Llama-3.1-Nemotron-70B-Instruct-HF_bfloat16_250db5cf2323e04a6d2025a2ca2b94a95c439e88_True,nvidia/Llama-3.1-Nemotron-70B-Instruct-HF,250db5cf2323e04a6d2025a2ca2b94a95c439e88,bfloat16,chatmodels,Original,LlamaForCausalLM,34.5783715382223,TRUE,IFEval,0.738067217205903,73.8067217205903,BBH,0.631600066889504,47.1095304937273,MATH Level 5,0.287009063444109,28.7009063444109,GPQA,0.258389261744966,1.11856823266219,MUSR,0.432760416666667,13.1950520833333,MMLU-PRO,0.491855053191489,43.5394503546099,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-12,2024-10-16,2,meta-llama/Meta-Llama-3.1-70B,llama3.1,1874,70.554,13.6287476336013 nvidia/Minitron-4B-Base_bfloat16_d6321f64412982046a32d761701167e752fedc02_False,nvidia/Minitron-4B-Base,d6321f64412982046a32d761701167e752fedc02,bfloat16,pretrained,Original,NemotronForCausalLM,11.9399727051767,FALSE,IFEval,0.221793729526545,22.1793729526545,BBH,0.40838762439925,17.2156006550611,MATH Level 5,0.0173716012084592,1.73716012084592,GPQA,0.269295302013423,2.57270693512304,MUSR,0.413375,9.93854166666667,MMLU-PRO,0.261968085106383,17.9964539007092,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-19,2024-09-25,0,nvidia/Minitron-4B-Base,other,127,4,1.18926681315643 nvidia/Minitron-8B-Base_bfloat16_70fa5997afc42807f41eebd5d481f040556fdf97_False,nvidia/Minitron-8B-Base,70fa5997afc42807f41eebd5d481f040556fdf97,bfloat16,pretrained,Original,NemotronForCausalLM,14.1787264154315,FALSE,IFEval,0.242426760994162,24.2426760994162,BBH,0.43950631883576,22.0407929700052,MATH Level 5,0.0234138972809668,2.34138972809668,GPQA,0.273489932885906,3.13199105145414,MUSR,0.402552083333333,9.08567708333334,MMLU-PRO,0.318068484042553,24.2298315602837,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-19,2024-09-25,0,nvidia/Minitron-8B-Base,other,63,7.22,1.41252072016633 nvidia/Mistral-NeMo-Minitron-8B-Base_bfloat16_cc94637b669b62c4829b1e0c3b9074fecd883b74_False,nvidia/Mistral-NeMo-Minitron-8B-Base,cc94637b669b62c4829b1e0c3b9074fecd883b74,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,17.6601615070764,FALSE,IFEval,0.194565973838305,19.4565973838305,BBH,0.521909809052142,31.8220151574902,MATH Level 5,0.0460725075528701,4.60725075528701,GPQA,0.325503355704698,10.0671140939597,MUSR,0.40915625,8.94453125,MMLU-PRO,0.379571143617021,31.0634604018913,TRUE,FALSE,FALSE,FALSE,TRUE,2024-08-19,2024-08-22,0,nvidia/Mistral-NeMo-Minitron-8B-Base,other,164,7.88,3.40402832024504 @@ -1795,8 +1795,8 @@ oobabooga/CodeBooga-34B-v0.1_float16_8a4e1e16ac46333cbd0c17d733d3d70a956071a6_Tr oopere/pruned20-llama-1b_float16_3351c9a062055ce6c16dd2c9f0c229fb5dd7396b_False,oopere/pruned20-llama-1b,3351c9a062055ce6c16dd2c9f0c229fb5dd7396b,float16,basemergesandmoerges,Original,LlamaForCausalLM,4.86363846042225,FALSE,IFEval,0.199362136907849,19.9362136907849,BBH,0.30313627830972,3.18539425984899,MATH Level 5,0.00302114803625378,0.302114803625378,GPQA,0.25,0,MUSR,0.363145833333333,4.39322916666667,MMLU-PRO,0.112283909574468,1.36487884160756,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-16,2024-11-16,1,oopere/pruned20-llama-1b (Merge),llama3.2,0,1.075,0.401478046019652 oopere/pruned40-llama-1b_float16_3de470d9c61cb57cea821e93b43fb250aa14b975_False,oopere/pruned40-llama-1b,3de470d9c61cb57cea821e93b43fb250aa14b975,float16,pretrained,Original,LlamaForCausalLM,6.49506415091076,FALSE,IFEval,0.228438321431579,22.8438321431579,BBH,0.296915638014199,2.65530893137662,MATH Level 5,0.000755287009063444,0.0755287009063444,GPQA,0.243288590604027,0,MUSR,0.428666666666667,12.4833333333333,MMLU-PRO,0.108211436170213,0.912381796690307,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-16,2024-11-26,1,oopere/pruned40-llama-1b (Merge),llama3.2,0,0.914,0.376621285485414 oopere/pruned60-llama-1b_float16_86b157256928b50ee07cc3cf5b3884b70062f2fe_False,oopere/pruned60-llama-1b,86b157256928b50ee07cc3cf5b3884b70062f2fe,float16,pretrained,Original,LlamaForCausalLM,5.42980237577008,FALSE,IFEval,0.182850392514085,18.2850392514085,BBH,0.30161934741854,2.94252648075335,MATH Level 5,0,0,GPQA,0.249161073825503,0,MUSR,0.408791666666667,9.43229166666667,MMLU-PRO,0.117270611702128,1.91895685579196,TRUE,FALSE,FALSE,FALSE,FALSE,2024-11-16,2024-11-25,1,oopere/pruned60-llama-1b (Merge),llama3.2,0,0.753,0.382487881515074 -openai-community/gpt2_bfloat16_607a30d783dfa663caf39e06633721c8d4cfcd7e_False,openai-community/gpt2,607a30d783dfa663caf39e06633721c8d4cfcd7e,bfloat16,pretrained,Original,GPT2LMHeadModel,6.51080708776172,FALSE,IFEval,0.179253270211927,17.9253270211927,BBH,0.303571124421336,2.67498136798699,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.258389261744966,1.11856823266219,MUSR,0.447052083333333,15.3481770833333,MMLU-PRO,0.115940824468085,1.77120271867612,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-12,0,openai-community/gpt2,mit,2436,0.137,0.0859412568146148 -openai-community/gpt2_float16_607a30d783dfa663caf39e06633721c8d4cfcd7e_False,openai-community/gpt2,607a30d783dfa663caf39e06633721c8d4cfcd7e,float16,pretrained,Original,GPT2LMHeadModel,6.29647106783872,FALSE,IFEval,0.177954494075719,17.7954494075719,BBH,0.301658010676531,2.81591130950851,MATH Level 5,0.00302114803625378,0.302114803625378,GPQA,0.258389261744966,1.11856823266219,MUSR,0.439020833333333,13.9109375,MMLU-PRO,0.116522606382979,1.8358451536643,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-08-12,0,openai-community/gpt2,mit,2436,0.137,0.117386895248811 +openai-community/gpt2_bfloat16_607a30d783dfa663caf39e06633721c8d4cfcd7e_False,openai-community/gpt2,607a30d783dfa663caf39e06633721c8d4cfcd7e,bfloat16,pretrained,Original,GPT2LMHeadModel,6.51080708776172,FALSE,IFEval,0.179253270211927,17.9253270211927,BBH,0.303571124421336,2.67498136798699,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.258389261744966,1.11856823266219,MUSR,0.447052083333333,15.3481770833333,MMLU-PRO,0.115940824468085,1.77120271867612,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-12,0,openai-community/gpt2,mit,2442,0.137,0.0859412568146148 +openai-community/gpt2_float16_607a30d783dfa663caf39e06633721c8d4cfcd7e_False,openai-community/gpt2,607a30d783dfa663caf39e06633721c8d4cfcd7e,float16,pretrained,Original,GPT2LMHeadModel,6.29647106783872,FALSE,IFEval,0.177954494075719,17.7954494075719,BBH,0.301658010676531,2.81591130950851,MATH Level 5,0.00302114803625378,0.302114803625378,GPQA,0.258389261744966,1.11856823266219,MUSR,0.439020833333333,13.9109375,MMLU-PRO,0.116522606382979,1.8358451536643,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-08-12,0,openai-community/gpt2,mit,2442,0.137,0.117386895248811 openai-community/gpt2-large_bfloat16_32b71b12589c2f8d625668d2335a01cac3249519_False,openai-community/gpt2-large,32b71b12589c2f8d625668d2335a01cac3249519,bfloat16,pretrained,Original,GPT2LMHeadModel,5.47959037520557,FALSE,IFEval,0.204782200117909,20.4782200117909,BBH,0.306884187601188,3.25379054497874,MATH Level 5,0.006797583081571,0.6797583081571,GPQA,0.259228187919463,1.23042505592841,MUSR,0.378864583333333,5.65807291666667,MMLU-PRO,0.114195478723404,1.57727541371158,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-12,0,openai-community/gpt2-large,mit,279,0.812,0.180462238431619 openai-community/gpt2-medium_bfloat16_6dcaa7a952f72f9298047fd5137cd6e4f05f41da_False,openai-community/gpt2-medium,6dcaa7a952f72f9298047fd5137cd6e4f05f41da,bfloat16,pretrained,Original,GPT2LMHeadModel,5.8268115862481,FALSE,IFEval,0.220844027181213,22.0844027181213,BBH,0.305028023217627,2.71997223835624,MATH Level 5,0.00302114803625378,0.302114803625378,GPQA,0.26258389261745,1.67785234899329,MUSR,0.388447916666667,6.15598958333333,MMLU-PRO,0.118184840425532,2.0205378250591,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-12,0,openai-community/gpt2-medium,mit,159,0.38,0.121061915000596 openai-community/gpt2-xl_bfloat16_15ea56dee5df4983c59b2538573817e1667135e2_False,openai-community/gpt2-xl,15ea56dee5df4983c59b2538573817e1667135e2,bfloat16,pretrained,Original,GPT2LMHeadModel,4.98018762739917,FALSE,IFEval,0.203857985700164,20.3857985700164,BBH,0.300857611232608,2.58096064745272,MATH Level 5,0.00302114803625378,0.302114803625378,GPQA,0.258389261744966,1.11856823266219,MUSR,0.370958333333333,4.03645833333333,MMLU-PRO,0.113115026595745,1.45722517730496,TRUE,FALSE,FALSE,FALSE,TRUE,2022-03-02,2024-06-12,0,openai-community/gpt2-xl,mit,316,1.608,0.215313699838485 @@ -1922,7 +1922,7 @@ recoilme/recoilme-gemma-2-9B-v0.4_bfloat16_2691f2cc8d80072f15d78cb7ae72831e1a121 recoilme/recoilme-gemma-2-9B-v0.5_float16_b4035d3a16486dae4f726eb953be959a4573ea67_True,recoilme/recoilme-gemma-2-9B-v0.5,b4035d3a16486dae4f726eb953be959a4573ea67,float16,chatmodels,Original,Gemma2ForCausalLM,30.0577620055673,TRUE,IFEval,0.766418658049531,76.6418658049531,BBH,0.5981472549925,42.3533554065342,MATH Level 5,0.0211480362537764,2.11480362537764,GPQA,0.336409395973154,11.5212527964206,MUSR,0.423177083333333,12.1638020833333,MMLU-PRO,0.419963430851064,35.5514923167849,FALSE,FALSE,FALSE,FALSE,FALSE,2024-11-26,2024-11-26,1,recoilme/recoilme-gemma-2-9B-v0.5 (Merge),"",0,10.159,3.86674425617504 refuelai/Llama-3-Refueled_bfloat16_ff6d1c3ba37b31d4af421951c2300f2256fb3691_True,refuelai/Llama-3-Refueled,ff6d1c3ba37b31d4af421951c2300f2256fb3691,bfloat16,chatmodels,Original,LlamaForCausalLM,22.8038048017426,TRUE,IFEval,0.461995283625226,46.1995283625226,BBH,0.587076620170505,41.721971003391,MATH Level 5,0.0438066465256798,4.38066465256798,GPQA,0.299496644295302,6.59955257270694,MUSR,0.44540625,14.6424479166667,MMLU-PRO,0.309507978723404,23.2786643026005,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-03,2024-06-12,0,refuelai/Llama-3-Refueled,cc-by-nc-4.0,189,8.03,0.875985833377866 rhplus0831/maid-yuzu-v7_bfloat16_a0bd8c707bb80024778da4a0d057917faa53d2f6_True,rhplus0831/maid-yuzu-v7,a0bd8c707bb80024778da4a0d057917faa53d2f6,bfloat16,chatmodels,Original,MixtralForCausalLM,24.4819301245243,TRUE,IFEval,0.646243079473575,64.6243079473575,BBH,0.480491692312673,26.8198371046094,MATH Level 5,0.0951661631419939,9.51661631419939,GPQA,0.309563758389262,7.94183445190157,MUSR,0.413625,9.76979166666667,MMLU-PRO,0.353972739361702,28.2191932624114,FALSE,FALSE,FALSE,FALSE,FALSE,2024-02-09,2024-09-08,1,rhplus0831/maid-yuzu-v7 (Merge),"",1,46.703,4.1042853231815 -rhymes-ai/Aria_bfloat16_5cc2703b3afd585f232ec5027e9c039a2001bcec_True,rhymes-ai/Aria,5cc2703b3afd585f232ec5027e9c039a2001bcec,bfloat16,multimodal,Original,AriaForConditionalGeneration,28.3540512057254,TRUE,IFEval,0.477307987251604,47.7307987251604,BBH,0.569531244641363,39.2814933548104,MATH Level 5,0.16238670694864,16.238670694864,GPQA,0.36241610738255,14.9888143176734,MUSR,0.43375,14.0520833333333,MMLU-PRO,0.440492021276596,37.8324468085106,TRUE,FALSE,TRUE,FALSE,TRUE,2024-09-26,2024-10-10,1,rhymes-ai/Aria (Merge),apache-2.0,593,25.307,7.75070962321425 +rhymes-ai/Aria_bfloat16_5cc2703b3afd585f232ec5027e9c039a2001bcec_True,rhymes-ai/Aria,5cc2703b3afd585f232ec5027e9c039a2001bcec,bfloat16,multimodal,Original,AriaForConditionalGeneration,28.3540512057254,TRUE,IFEval,0.477307987251604,47.7307987251604,BBH,0.569531244641363,39.2814933548104,MATH Level 5,0.16238670694864,16.238670694864,GPQA,0.36241610738255,14.9888143176734,MUSR,0.43375,14.0520833333333,MMLU-PRO,0.440492021276596,37.8324468085106,TRUE,FALSE,TRUE,FALSE,TRUE,2024-09-26,2024-10-10,1,rhymes-ai/Aria (Merge),apache-2.0,594,25.307,7.75070962321425 rhysjones/phi-2-orange-v2_float16_f4085189114accfb65225deb8fbdf15767b7ee56_True,rhysjones/phi-2-orange-v2,f4085189114accfb65225deb8fbdf15767b7ee56,float16,fine-tunedondomain-specificdatasets,Original,PhiForCausalLM,14.644426788214,TRUE,IFEval,0.36697407323679,36.697407323679,BBH,0.477022010981621,25.6065488373247,MATH Level 5,0,0,GPQA,0.261744966442953,1.56599552572707,MUSR,0.362958333333333,6.96979166666667,MMLU-PRO,0.253241356382979,17.0268173758865,TRUE,FALSE,FALSE,FALSE,FALSE,2024-03-04,2024-06-28,0,rhysjones/phi-2-orange-v2,mit,27,2.78,0.470949345404158 riaz/FineLlama-3.1-8B_bfloat16_c4d8f16eb446910edce0c1afd0e6d5f3b06e2e7d_True,riaz/FineLlama-3.1-8B,c4d8f16eb446910edce0c1afd0e6d5f3b06e2e7d,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,17.6102955930295,TRUE,IFEval,0.437340700452577,43.7340700452577,BBH,0.458572964980135,24.1487780916786,MATH Level 5,0.0483383685800604,4.83383685800604,GPQA,0.275167785234899,3.35570469798658,MUSR,0.376291666666667,7.76979166666667,MMLU-PRO,0.296376329787234,21.8195921985816,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-07,2024-10-12,2,meta-llama/Meta-Llama-3.1-8B,apache-2.0,1,8.03,0.921091580515014 riaz/FineLlama-3.1-8B_float16_c4d8f16eb446910edce0c1afd0e6d5f3b06e2e7d_True,riaz/FineLlama-3.1-8B,c4d8f16eb446910edce0c1afd0e6d5f3b06e2e7d,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,17.1475109567192,TRUE,IFEval,0.413660199382084,41.3660199382084,BBH,0.456451981676995,23.7733895905397,MATH Level 5,0.0453172205438067,4.53172205438067,GPQA,0.276006711409396,3.4675615212528,MUSR,0.377625,7.76979166666667,MMLU-PRO,0.297789228723404,21.9765809692671,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-07,2024-10-12,2,meta-llama/Meta-Llama-3.1-8B,apache-2.0,1,8.03,0.901997901327406 @@ -1930,7 +1930,7 @@ rmdhirr/Gluon-8B_float16_cc949908c60ab7f696e133714222d6cab156e493_False,rmdhirr/ rombodawg/Rombos-LLM-V2.5-Qwen-0.5b_bfloat16_aae2e55548c8090ce357c64ca78e8b9ef6baf118_False,rombodawg/Rombos-LLM-V2.5-Qwen-0.5b,aae2e55548c8090ce357c64ca78e8b9ef6baf118,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,8.71874980353985,FALSE,IFEval,0.284666906031552,28.4666906031552,BBH,0.329367518314363,8.41221856626973,MATH Level 5,0.0279456193353474,2.79456193353474,GPQA,0.266778523489933,2.23713646532438,MUSR,0.323583333333333,0.78125,MMLU-PRO,0.186585771276596,9.62064125295508,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-06,2024-09-29,1,rombodawg/Rombos-LLM-V2.5-Qwen-0.5b (Merge),apache-2.0,3,0.63,0.645706811989279 rombodawg/Rombos-LLM-V2.5-Qwen-1.5b_bfloat16_1f634da015ed671efe7dc574bc2a1954f5b2cc93_False,rombodawg/Rombos-LLM-V2.5-Qwen-1.5b,1f634da015ed671efe7dc574bc2a1954f5b2cc93,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,16.1655641449128,FALSE,IFEval,0.340246102563421,34.0246102563421,BBH,0.425670314586439,18.7113437839723,MATH Level 5,0.0740181268882175,7.40181268882175,GPQA,0.288590604026846,5.14541387024609,MUSR,0.418552083333333,10.35234375,MMLU-PRO,0.292220744680851,21.3578605200946,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-06,2024-09-29,1,rombodawg/Rombos-LLM-V2.5-Qwen-1.5b (Merge),apache-2.0,3,1.777,0.740357996195001 rombodawg/Rombos-LLM-V2.5-Qwen-14b_bfloat16_834ddb1712ae6d1b232b2d5b26be658d90d23e43_False,rombodawg/Rombos-LLM-V2.5-Qwen-14b,834ddb1712ae6d1b232b2d5b26be658d90d23e43,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,34.7300596437434,FALSE,IFEval,0.584044778964259,58.4044778964259,BBH,0.648108626166965,49.3869002714448,MATH Level 5,0.169184290030212,16.9184290030212,GPQA,0.371644295302013,16.2192393736018,MUSR,0.471729166666667,18.8328125,MMLU-PRO,0.537566489361702,48.6184988179669,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-06,2024-09-29,1,rombodawg/Rombos-LLM-V2.5-Qwen-14b (Merge),apache-2.0,5,14.77,2.18269986161066 -rombodawg/Rombos-LLM-V2.5-Qwen-32b_bfloat16_234abe4b494dbe83ba805b791f74feb33462a33d_False,rombodawg/Rombos-LLM-V2.5-Qwen-32b,234abe4b494dbe83ba805b791f74feb33462a33d,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,44.57420016657,FALSE,IFEval,0.682663111654854,68.2663111654854,BBH,0.70455370708598,58.2618940867874,MATH Level 5,0.419939577039275,41.9939577039275,GPQA,0.396812080536913,19.5749440715884,MUSR,0.503416666666667,24.7270833333333,MMLU-PRO,0.591589095744681,54.6210106382979,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-30,2024-10-07,1,rombodawg/Rombos-LLM-V2.5-Qwen-32b (Merge),apache-2.0,37,32.764,17.9126897235194 +rombodawg/Rombos-LLM-V2.5-Qwen-32b_bfloat16_234abe4b494dbe83ba805b791f74feb33462a33d_False,rombodawg/Rombos-LLM-V2.5-Qwen-32b,234abe4b494dbe83ba805b791f74feb33462a33d,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,44.57420016657,FALSE,IFEval,0.682663111654854,68.2663111654854,BBH,0.70455370708598,58.2618940867874,MATH Level 5,0.419939577039275,41.9939577039275,GPQA,0.396812080536913,19.5749440715884,MUSR,0.503416666666667,24.7270833333333,MMLU-PRO,0.591589095744681,54.6210106382979,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-30,2024-10-07,1,rombodawg/Rombos-LLM-V2.5-Qwen-32b (Merge),apache-2.0,38,32.764,17.9126897235194 rombodawg/Rombos-LLM-V2.5-Qwen-3b_bfloat16_26601a8da5afce3b5959d91bdd0faaab6df8bf95_False,rombodawg/Rombos-LLM-V2.5-Qwen-3b,26601a8da5afce3b5959d91bdd0faaab6df8bf95,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,22.1831113569493,FALSE,IFEval,0.534235827604091,53.4235827604091,BBH,0.480889624636847,27.2135969511257,MATH Level 5,0.0551359516616314,5.51359516616314,GPQA,0.307885906040268,7.71812080536913,MUSR,0.404166666666667,8.55416666666667,MMLU-PRO,0.37608045212766,30.6756057919622,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-06,2024-09-29,1,rombodawg/Rombos-LLM-V2.5-Qwen-3b (Merge),other,3,3.397,1.005794477103 rombodawg/Rombos-LLM-V2.5-Qwen-72b_bfloat16_5260f182e7859e13d515c4cb3926ac85ad057504_False,rombodawg/Rombos-LLM-V2.5-Qwen-72b,5260f182e7859e13d515c4cb3926ac85ad057504,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,45.9092456451536,FALSE,IFEval,0.715535889218385,71.5535889218385,BBH,0.722958906578849,61.2671450457366,MATH Level 5,0.506797583081571,50.6797583081571,GPQA,0.398489932885906,19.7986577181208,MUSR,0.459916666666667,17.3229166666667,MMLU-PRO,0.593500664893617,54.8334072104019,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-30,2024-09-30,1,rombodawg/Rombos-LLM-V2.5-Qwen-72b (Merge),other,29,72,16.0339456258967 rombodawg/Rombos-LLM-V2.5-Qwen-7b_bfloat16_dbd819e8f765181f774cb5b79812d081669eb302_False,rombodawg/Rombos-LLM-V2.5-Qwen-7b,dbd819e8f765181f774cb5b79812d081669eb302,bfloat16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,31.1123483495661,FALSE,IFEval,0.623711751486057,62.3711751486057,BBH,0.554388504690359,36.3723504143006,MATH Level 5,0.283232628398792,28.3232628398792,GPQA,0.317953020134228,9.06040268456376,MUSR,0.42909375,12.0033854166667,MMLU-PRO,0.446891622340426,38.5435135933806,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-06,2024-09-29,1,rombodawg/Rombos-LLM-V2.5-Qwen-7b (Merge),apache-2.0,15,7.616,1.31708405545612 @@ -1958,7 +1958,7 @@ saltlux/luxia-21.4b-alignment-v1.0_float16_87d5673e6d9f60462f195e9414a0bf6874c89 saltlux/luxia-21.4b-alignment-v1.2_bfloat16_eed12b5574fa49cc81e57a88aff24c08c13721c0_True,saltlux/luxia-21.4b-alignment-v1.2,eed12b5574fa49cc81e57a88aff24c08c13721c0,bfloat16,chatmodels,Original,LlamaForCausalLM,23.4351918455184,TRUE,IFEval,0.411536944196953,41.1536944196953,BBH,0.637118070811237,47.7691647188475,MATH Level 5,0.0158610271903323,1.58610271903323,GPQA,0.307885906040268,7.71812080536913,MUSR,0.445895833333333,14.9036458333333,MMLU-PRO,0.347323803191489,27.4804225768322,TRUE,FALSE,FALSE,FALSE,FALSE,2024-05-27,2024-07-30,0,saltlux/luxia-21.4b-alignment-v1.2,apache-2.0,8,21.421,2.04592577623435 sam-paech/Darkest-muse-v1_bfloat16_55f6ba0218e9615d18a76f244a874b941f8c434f_False,sam-paech/Darkest-muse-v1,55f6ba0218e9615d18a76f244a874b941f8c434f,bfloat16,basemergesandmoerges,Original,Gemma2ForCausalLM,31.810869013554,FALSE,IFEval,0.734420227219334,73.4420227219334,BBH,0.596843953070895,42.6117312683706,MATH Level 5,0.11631419939577,11.631419939577,GPQA,0.343959731543624,12.5279642058166,MUSR,0.450208333333333,15.2760416666667,MMLU-PRO,0.418384308510638,35.3760342789598,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-22,2024-10-26,1,sam-paech/Darkest-muse-v1 (Merge),apache-2.0,22,10.159,2.20694726611163 sam-paech/Delirium-v1_bfloat16_98dc2dad47af405013c0584d752504ca448bd8eb_False,sam-paech/Delirium-v1,98dc2dad47af405013c0584d752504ca448bd8eb,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,31.732318132305,FALSE,IFEval,0.720756481690803,72.0756481690803,BBH,0.596211383452173,42.3150790899333,MATH Level 5,0.129154078549849,12.9154078549849,GPQA,0.343120805369128,12.4161073825503,MUSR,0.451447916666667,15.2309895833333,MMLU-PRO,0.418966090425532,35.440676713948,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-17,2024-10-26,1,unsloth/gemma-2-9b-it,gemma,9,9.242,2.3955012459142 -sam-paech/Quill-v1_bfloat16_3cab1cac9d3de0d25b48ea86b4533aa220231f20_False,sam-paech/Quill-v1,3cab1cac9d3de0d25b48ea86b4533aa220231f20,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,31.5030208676919,FALSE,IFEval,0.712213593265868,71.2213593265868,BBH,0.596922634798949,42.5976691390359,MATH Level 5,0.118580060422961,11.8580060422961,GPQA,0.339765100671141,11.9686800894855,MUSR,0.455479166666667,16.1348958333333,MMLU-PRO,0.417137632978723,35.2375147754137,FALSE,FALSE,FALSE,FALSE,FALSE,2024-10-20,2024-10-26,1,sam-paech/Quill-v1 (Merge),"",4,9.242,2.31346910671926 +sam-paech/Quill-v1_bfloat16_3cab1cac9d3de0d25b48ea86b4533aa220231f20_False,sam-paech/Quill-v1,3cab1cac9d3de0d25b48ea86b4533aa220231f20,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,31.5030208676919,FALSE,IFEval,0.712213593265868,71.2213593265868,BBH,0.596922634798949,42.5976691390359,MATH Level 5,0.118580060422961,11.8580060422961,GPQA,0.339765100671141,11.9686800894855,MUSR,0.455479166666667,16.1348958333333,MMLU-PRO,0.417137632978723,35.2375147754137,FALSE,FALSE,FALSE,FALSE,FALSE,2024-10-20,2024-10-26,1,sam-paech/Quill-v1 (Merge),"",5,9.242,2.31346910671926 schnapss/testmerge-7b_bfloat16_ff84f5b87ba51db9622b1c553c076533890a8f50_False,schnapss/testmerge-7b,ff84f5b87ba51db9622b1c553c076533890a8f50,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,20.9134460848223,FALSE,IFEval,0.392228176793131,39.2228176793131,BBH,0.518747840563738,32.6381662414967,MATH Level 5,0.0687311178247734,6.87311178247734,GPQA,0.296140939597315,6.15212527964205,MUSR,0.4685625,17.7036458333333,MMLU-PRO,0.306017287234043,22.8908096926714,FALSE,FALSE,FALSE,FALSE,FALSE,2024-11-16,2024-11-16,1,schnapss/testmerge-7b (Merge),"",0,7.242,0.470154717477583 sci-m-wang/Mistral-7B-Instruct-sa-v0.1_bfloat16_2dcff66eac0c01dc50e4c41eea959968232187fe_True,sci-m-wang/Mistral-7B-Instruct-sa-v0.1,2dcff66eac0c01dc50e4c41eea959968232187fe,bfloat16,chatmodels,Adapter,?,12.2000642869982,TRUE,IFEval,0.433518619485188,43.3518619485188,BBH,0.327278215614117,5.74364607742995,MATH Level 5,0.0105740181268882,1.05740181268882,GPQA,0.259228187919463,1.23042505592841,MUSR,0.39,6.68333333333333,MMLU-PRO,0.236203457446809,15.1337174940898,TRUE,FALSE,FALSE,FALSE,FALSE,2024-05-31,2024-06-27,2,mistralai/Mistral-7B-v0.1,other,0,14.483,0.765082309391731 sci-m-wang/Phi-3-mini-4k-instruct-sa-v0.1_bfloat16_5a516f86087853f9d560c95eb9209c1d4ed9ff69_True,sci-m-wang/Phi-3-mini-4k-instruct-sa-v0.1,5a516f86087853f9d560c95eb9209c1d4ed9ff69,bfloat16,chatmodels,Adapter,?,25.7737920491517,TRUE,IFEval,0.502062305793073,50.2062305793073,BBH,0.550203872238305,36.6054191487681,MATH Level 5,0.145015105740181,14.5015105740181,GPQA,0.328859060402685,10.5145413870246,MUSR,0.407302083333333,9.64609375,MMLU-PRO,0.398520611702128,33.168956855792,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-01,2024-06-27,1,microsoft/Phi-3-mini-4k-instruct,other,0,7.642,1.28050267506016 @@ -1971,7 +1971,7 @@ sequelbox/Llama3.1-8B-PlumChat_float16_1afdc9856591f573e4fcb52dba19a9d8da631e0b_ sequelbox/Llama3.1-8B-PlumCode_float16_171cd599d574000607491f08e6cf7b7eb199e33d_False,sequelbox/Llama3.1-8B-PlumCode,171cd599d574000607491f08e6cf7b7eb199e33d,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,9.81141178260326,FALSE,IFEval,0.204482994011445,20.4482994011445,BBH,0.336808686142542,8.50292727164202,MATH Level 5,0.0264350453172205,2.64350453172205,GPQA,0.276006711409396,3.4675615212528,MUSR,0.37734375,8.96796875,MMLU-PRO,0.233543882978723,14.8382092198582,TRUE,TRUE,FALSE,FALSE,FALSE,2024-10-02,2024-10-03,1,sequelbox/Llama3.1-8B-PlumCode (Merge),llama3.1,0,8.03,0.890676247897503 sequelbox/Llama3.1-8B-PlumMath_float16_b857c30a626f7c020fcba89df7bece4bb7381ac2_False,sequelbox/Llama3.1-8B-PlumMath,b857c30a626f7c020fcba89df7bece4bb7381ac2,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,13.8863326072413,FALSE,IFEval,0.224241678745728,22.4241678745728,BBH,0.403230230900481,16.4465838289458,MATH Level 5,0.0445619335347432,4.45619335347432,GPQA,0.317953020134228,9.06040268456376,MUSR,0.391854166666667,8.98177083333333,MMLU-PRO,0.297539893617021,21.9488770685579,TRUE,TRUE,FALSE,FALSE,FALSE,2024-10-01,2024-10-03,1,sequelbox/Llama3.1-8B-PlumMath (Merge),llama3.1,1,8.03,0.868772188246512 sequelbox/gemma-2-9B-MOTH_float16_8dff98ab82ba0087706afa0d6c69874a45548212_True,sequelbox/gemma-2-9B-MOTH,8dff98ab82ba0087706afa0d6c69874a45548212,float16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,4.55332423179952,TRUE,IFEval,0.205881505516474,20.5881505516474,BBH,0.307970005215625,3.21221723004962,MATH Level 5,0,0,GPQA,0.26006711409396,1.34228187919463,MUSR,0.340947916666667,0.618489583333333,MMLU-PRO,0.114029255319149,1.5588061465721,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-09,2024-09-10,2,google/gemma-2-9b,gemma,0,9.242,3.02794894307461 -sethuiyer/Qwen2.5-7B-Anvita_bfloat16_dc6f8ca6507cc282938e70b23b02c1a3db7b7ddc_True,sethuiyer/Qwen2.5-7B-Anvita,dc6f8ca6507cc282938e70b23b02c1a3db7b7ddc,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,29.180839462378,TRUE,IFEval,0.648041640624654,64.8041640624654,BBH,0.546586026678431,35.4824475238858,MATH Level 5,0.158610271903323,15.8610271903323,GPQA,0.327181208053691,10.2908277404922,MUSR,0.43365625,13.4736979166667,MMLU-PRO,0.41655585106383,35.1728723404255,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-10-27,0,Removed,"",0,7.616,1.08012331223306 +sethuiyer/Qwen2.5-7B-Anvita_bfloat16_dc6f8ca6507cc282938e70b23b02c1a3db7b7ddc_True,sethuiyer/Qwen2.5-7B-Anvita,dc6f8ca6507cc282938e70b23b02c1a3db7b7ddc,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,29.180839462378,TRUE,IFEval,0.648041640624654,64.8041640624654,BBH,0.546586026678431,35.4824475238858,MATH Level 5,0.158610271903323,15.8610271903323,GPQA,0.327181208053691,10.2908277404922,MUSR,0.43365625,13.4736979166667,MMLU-PRO,0.41655585106383,35.1728723404255,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-11,2024-10-27,1,sethuiyer/Qwen2.5-7B-Anvita (Merge),apache-2.0,1,7.616,1.08012331223306 shadowml/BeagSake-7B_bfloat16_b7a3b25a188a4608fd05fc4247ddd504c1f529d1_True,shadowml/BeagSake-7B,b7a3b25a188a4608fd05fc4247ddd504c1f529d1,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,19.0636978132577,TRUE,IFEval,0.521596031862126,52.1596031862126,BBH,0.471103423710985,25.1929446431132,MATH Level 5,0.054380664652568,5.4380664652568,GPQA,0.281040268456376,4.13870246085012,MUSR,0.412354166666667,9.84427083333333,MMLU-PRO,0.258477393617021,17.6085992907801,TRUE,TRUE,FALSE,FALSE,FALSE,2024-01-31,2024-10-29,1,shadowml/BeagSake-7B (Merge),cc-by-nc-4.0,1,7.242,2.8801279522073 shadowml/Mixolar-4x7b_float16_bb793526b063765e9861cad8834160fb0945e66d_False,shadowml/Mixolar-4x7b,bb793526b063765e9861cad8834160fb0945e66d,float16,basemergesandmoerges,Original,MixtralForCausalLM,19.283411530495,FALSE,IFEval,0.389330310243487,38.9330310243487,BBH,0.52159498762215,32.7289635762997,MATH Level 5,0,0,GPQA,0.292785234899329,5.70469798657718,MUSR,0.42575,12.71875,MMLU-PRO,0.330535239361702,25.6150265957447,TRUE,TRUE,TRUE,FALSE,FALSE,2023-12-30,2024-08-05,0,shadowml/Mixolar-4x7b,apache-2.0,3,36.099,2.35472770032513 shastraai/Shastra-LLAMA2-Math-Commonsense-SFT_bfloat16_97a578246d4edecb5fde3dae262a64e4ec9f489a_False,shastraai/Shastra-LLAMA2-Math-Commonsense-SFT,97a578246d4edecb5fde3dae262a64e4ec9f489a,bfloat16,basemergesandmoerges,Original,LlamaForCausalLM,10.5033471946029,FALSE,IFEval,0.304150764416193,30.4150764416194,BBH,0.384316753625765,13.6595232413437,MATH Level 5,0.0181268882175227,1.81268882175227,GPQA,0.259228187919463,1.23042505592841,MUSR,0.360447916666667,4.82265625,MMLU-PRO,0.199717420212766,11.079713356974,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-10-27,0,Removed,"",0,6.738,0.764042236102292 @@ -1980,12 +1980,12 @@ shivam9980/mistral-7b-news-cnn-merged_float16_a0d7029cb00c122843aef3d7ad61d514de shyamieee/Padma-v7.0_bfloat16_caf70bd6e2f819cc6a18dda8516f2cbdc101fdde_False,shyamieee/Padma-v7.0,caf70bd6e2f819cc6a18dda8516f2cbdc101fdde,bfloat16,basemergesandmoerges,Original,MistralForCausalLM,19.7562184101072,FALSE,IFEval,0.38410971777107,38.410971777107,BBH,0.511878563176149,31.6575207648742,MATH Level 5,0.0702416918429003,7.02416918429003,GPQA,0.286073825503356,4.80984340044743,MUSR,0.438552083333333,14.0856770833333,MMLU-PRO,0.302942154255319,22.549128250591,TRUE,TRUE,FALSE,FALSE,FALSE,2024-06-26,2024-06-26,1,shyamieee/Padma-v7.0 (Merge),apache-2.0,0,7.242,0.589898977749525 silma-ai/SILMA-9B-Instruct-v1.0_bfloat16_25d7b116ab3fb9f97417a297f8df4a7e34e7de68_True,silma-ai/SILMA-9B-Instruct-v1.0,25d7b116ab3fb9f97417a297f8df4a7e34e7de68,bfloat16,fine-tunedondomain-specificdatasets,Original,Gemma2ForCausalLM,24.3694419257046,TRUE,IFEval,0.584194382017491,58.4194382017492,BBH,0.52190150328535,30.7130026297921,MATH Level 5,0,0,GPQA,0.305369127516779,7.38255033557047,MUSR,0.463697916666667,17.2622395833333,MMLU-PRO,0.391954787234043,32.4394208037825,TRUE,FALSE,FALSE,FALSE,FALSE,2024-08-17,2024-11-12,0,silma-ai/SILMA-9B-Instruct-v1.0,gemma,54,9.242,1.24599891429288 skymizer/Llama2-7b-sft-chat-custom-template-dpo_bfloat16_22302ebd8c551a5f302fcb8366cc61fdeedf0e00_False,skymizer/Llama2-7b-sft-chat-custom-template-dpo,22302ebd8c551a5f302fcb8366cc61fdeedf0e00,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,10.0901957146755,FALSE,IFEval,0.235282384074256,23.5282384074256,BBH,0.368846623026616,11.2388650744788,MATH Level 5,0.0113293051359517,1.13293051359517,GPQA,0.239093959731544,0,MUSR,0.442864583333333,14.1247395833333,MMLU-PRO,0.194647606382979,10.5164007092199,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-11,2024-07-01,1,Removed,llama2,0,6.738,0.616470441674189 -sometimesanotion/Lamarck-14B-v0.1-experimental_bfloat16_b0600e08e8c97b25d1abca543b997d9927245442_False,sometimesanotion/Lamarck-14B-v0.1-experimental,b0600e08e8c97b25d1abca543b997d9927245442,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,36.6709959612302,FALSE,IFEval,0.535385000687066,53.5385000687066,BBH,0.658253923996733,50.7949076691947,MATH Level 5,0.305135951661631,30.5135951661631,GPQA,0.381711409395973,17.5615212527964,MUSR,0.47284375,18.6388020833333,MMLU-PRO,0.540807845744681,48.9786495271868,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-12-09,0,Removed,"",0,14.766,1.8946933781146 +sometimesanotion/Lamarck-14B-v0.1-experimental_bfloat16_b0600e08e8c97b25d1abca543b997d9927245442_False,sometimesanotion/Lamarck-14B-v0.1-experimental,b0600e08e8c97b25d1abca543b997d9927245442,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,36.6709959612302,FALSE,IFEval,0.535385000687066,53.5385000687066,BBH,0.658253923996733,50.7949076691947,MATH Level 5,0.305135951661631,30.5135951661631,GPQA,0.381711409395973,17.5615212527964,MUSR,0.47284375,18.6388020833333,MMLU-PRO,0.540807845744681,48.9786495271868,TRUE,TRUE,FALSE,FALSE,FALSE,2024-12-01,2024-12-09,1,sometimesanotion/Lamarck-14B-v0.1-experimental (Merge),apache-2.0,1,14.766,1.8946933781146 sometimesanotion/Lamarck-14B-v0.3_bfloat16_781637d1b65766fe933ebde070632e48f91390ab_False,sometimesanotion/Lamarck-14B-v0.3,781637d1b65766fe933ebde070632e48f91390ab,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,36.5760956938364,FALSE,IFEval,0.503161611191638,50.3161611191638,BBH,0.661140046537316,51.2743085882105,MATH Level 5,0.324018126888218,32.4018126888218,GPQA,0.388422818791946,18.4563758389262,MUSR,0.4688125,18.0015625,MMLU-PRO,0.541057180851064,49.006353427896,TRUE,TRUE,FALSE,FALSE,FALSE,2024-12-06,2024-12-09,1,sometimesanotion/Lamarck-14B-v0.3 (Merge),apache-2.0,2,14.766,7.63918131611033 sometimesanotion/Lamarck-14B-v0.4-Qwenvergence_bfloat16_add9a151dd5614603bebcf3d3740fa92e5d67632_False,sometimesanotion/Lamarck-14B-v0.4-Qwenvergence,add9a151dd5614603bebcf3d3740fa92e5d67632,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,36.5697935328493,FALSE,IFEval,0.490647038746083,49.0647038746083,BBH,0.653514219232406,50.2080449984793,MATH Level 5,0.336858006042296,33.6858006042296,GPQA,0.378355704697987,17.1140939597315,MUSR,0.4846875,20.3859375,MMLU-PRO,0.540641622340426,48.9601802600473,TRUE,TRUE,FALSE,FALSE,FALSE,2024-12-12,2024-12-12,1,sometimesanotion/Lamarck-14B-v0.4-Qwenvergence (Merge),apache-2.0,0,14,1.74126349788564 sometimesanotion/Qwen-2.5-14B-Virmarckeoso_bfloat16__False,sometimesanotion/Qwen-2.5-14B-Virmarckeoso,"",bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,36.2459325944883,FALSE,IFEval,0.481329538956635,48.1329538956635,BBH,0.656972995077668,50.6522948701311,MATH Level 5,0.333081570996979,33.3081570996979,GPQA,0.379194630872483,17.2259507829978,MUSR,0.479354166666667,19.5192708333333,MMLU-PRO,0.537732712765958,48.6369680851064,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-12-10,0,Removed,"",0,14.766,2.39515471362645 sometimesanotion/Qwen2.5-14B-Vimarckoso_bfloat16_0865365f6c0b221c08fdd5adf8965f3720645226_False,sometimesanotion/Qwen2.5-14B-Vimarckoso,0865365f6c0b221c08fdd5adf8965f3720645226,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,35.9058839126704,FALSE,IFEval,0.457424079220912,45.7424079220912,BBH,0.644634839005635,49.1789564154463,MATH Level 5,0.329305135951662,32.9305135951662,GPQA,0.39261744966443,19.0156599552573,MUSR,0.485864583333333,20.46640625,MMLU-PRO,0.532912234042553,48.1013593380615,TRUE,TRUE,FALSE,FALSE,FALSE,2024-12-11,2024-12-11,1,sometimesanotion/Qwen2.5-14B-Vimarckoso (Merge),apache-2.0,0,14,1.56765919047279 -sometimesanotion/lamarck-14b-prose-model_stock_bfloat16_d71942f5b5471fca97914ea26a9f66bb5866693e_False,sometimesanotion/lamarck-14b-prose-model_stock,d71942f5b5471fca97914ea26a9f66bb5866693e,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,35.5898576058715,FALSE,IFEval,0.427648638944667,42.7648638944667,BBH,0.648762158566534,49.383875963762,MATH Level 5,0.336102719033233,33.6102719033233,GPQA,0.393456375838926,19.1275167785235,MUSR,0.48459375,20.27421875,MMLU-PRO,0.535405585106383,48.3783983451537,FALSE,FALSE,FALSE,FALSE,FALSE,2024-12-06,2024-12-09,1,sometimesanotion/lamarck-14b-prose-model_stock (Merge),"",2,14.766,1.55751948598314 +sometimesanotion/lamarck-14b-prose-model_stock_bfloat16_d71942f5b5471fca97914ea26a9f66bb5866693e_False,sometimesanotion/lamarck-14b-prose-model_stock,d71942f5b5471fca97914ea26a9f66bb5866693e,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,35.5898576058715,FALSE,IFEval,0.427648638944667,42.7648638944667,BBH,0.648762158566534,49.383875963762,MATH Level 5,0.336102719033233,33.6102719033233,GPQA,0.393456375838926,19.1275167785235,MUSR,0.48459375,20.27421875,MMLU-PRO,0.535405585106383,48.3783983451537,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-12-09,0,Removed,"",0,14.766,1.55751948598314 sometimesanotion/lamarck-14b-reason-model_stock_bfloat16_0f1d7f04b9219ffe3bc26aa3146380fba249d61a_False,sometimesanotion/lamarck-14b-reason-model_stock,0f1d7f04b9219ffe3bc26aa3146380fba249d61a,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,36.2563275132583,FALSE,IFEval,0.496467151602193,49.6467151602193,BBH,0.656889854140825,50.715404125685,MATH Level 5,0.31570996978852,31.570996978852,GPQA,0.384228187919463,17.8970917225951,MUSR,0.474083333333333,18.79375,MMLU-PRO,0.540226063829787,48.9140070921986,FALSE,FALSE,FALSE,FALSE,FALSE,"",2024-12-09,0,Removed,"",0,14.766,7.94839884559841 sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-161415_float16_467eff1ac1c3395c130929bbe1f34a8194715e7c_True,sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-161415,467eff1ac1c3395c130929bbe1f34a8194715e7c,float16,chatmodels,Adapter,?,8.8268740255258,TRUE,IFEval,0.289337845804687,28.9337845804687,BBH,0.380418168868286,12.7892123094856,MATH Level 5,0.00755287009063444,0.755287009063444,GPQA,0.246644295302013,0,MUSR,0.3860625,6.02447916666667,MMLU-PRO,0.140126329787234,4.45848108747045,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-15,2024-10-16,1,unsloth/zephyr-sft-bnb-4bit,apache-2.0,0,7.723,1.62771156469603 sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-164205_float16_467eff1ac1c3395c130929bbe1f34a8194715e7c_True,sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-164205,467eff1ac1c3395c130929bbe1f34a8194715e7c,float16,chatmodels,Adapter,?,12.818811383335,TRUE,IFEval,0.319937765129856,31.9937765129856,BBH,0.395862436989292,16.7107251541481,MATH Level 5,0.00151057401812689,0.151057401812689,GPQA,0.276006711409396,3.4675615212528,MUSR,0.427177083333333,12.0971354166667,MMLU-PRO,0.212433510638298,12.4926122931442,TRUE,FALSE,FALSE,FALSE,FALSE,2024-10-15,2024-10-16,1,unsloth/zephyr-sft-bnb-4bit,apache-2.0,0,7.723,1.58899814826256 @@ -2060,8 +2060,8 @@ thomas-yanxin/XinYuan-Qwen2-7B_float16_c62d83eee2f4812ac17fc17d307f4aa1a77c5359_ thomas-yanxin/XinYuan-Qwen2-7B-0917_float16_6cee1b155fca9ae1f558f434953dfdadb9596af0_True,thomas-yanxin/XinYuan-Qwen2-7B-0917,6cee1b155fca9ae1f558f434953dfdadb9596af0,float16,fine-tunedondomain-specificdatasets,Original,Qwen2ForCausalLM,22.7216165321403,TRUE,IFEval,0.371919839359566,37.1919839359566,BBH,0.516921557378601,32.6199381358211,MATH Level 5,0.088368580060423,8.8368580060423,GPQA,0.309563758389262,7.94183445190157,MUSR,0.440104166666667,13.6796875,MMLU-PRO,0.424534574468085,36.0593971631206,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-17,2024-09-17,0,thomas-yanxin/XinYuan-Qwen2-7B-0917,other,4,7.616,1.48556449363563 thomas-yanxin/XinYuan-Qwen2.5-7B-0917_float16_bbbeafd1003c4d5e13f09b7223671957384b961a_True,thomas-yanxin/XinYuan-Qwen2.5-7B-0917,bbbeafd1003c4d5e13f09b7223671957384b961a,float16,chatmodels,Original,Qwen2ForCausalLM,18.1750369812353,TRUE,IFEval,0.357706441131753,35.7706441131753,BBH,0.518410611698749,33.439669270242,MATH Level 5,0,0,GPQA,0.281040268456376,4.13870246085012,MUSR,0.367552083333333,3.67734375,MMLU-PRO,0.388214760638298,32.0238622931442,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-17,2024-09-24,0,thomas-yanxin/XinYuan-Qwen2.5-7B-0917,other,4,7.616,0.971225233350759 tiiuae/falcon-11B_bfloat16_066e3bf4e2d9aaeefa129af0a6d39727d27816b3_False,tiiuae/falcon-11B,066e3bf4e2d9aaeefa129af0a6d39727d27816b3,bfloat16,pretrained,Original,FalconForCausalLM,13.814138235727,FALSE,IFEval,0.326132439704429,32.6132439704429,BBH,0.439163703554938,21.9379994628903,MATH Level 5,0.0256797583081571,2.56797583081571,GPQA,0.270973154362416,2.79642058165548,MUSR,0.398645833333333,7.53072916666667,MMLU-PRO,0.238946143617021,15.4384604018913,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-09,2024-06-09,0,tiiuae/falcon-11B,unknown,212,11.103,1.08287099141766 -tiiuae/falcon-40b_bfloat16_4a70170c215b36a3cce4b4253f6d0612bb7d4146_False,tiiuae/falcon-40b,4a70170c215b36a3cce4b4253f6d0612bb7d4146,bfloat16,pretrained,Original,FalconForCausalLM,11.3635401118469,FALSE,IFEval,0.249645385355302,24.9645385355302,BBH,0.40185324955958,16.5833047303122,MATH Level 5,0.0158610271903323,1.58610271903323,GPQA,0.273489932885906,3.13199105145414,MUSR,0.363145833333333,5.19322916666667,MMLU-PRO,0.250498670212766,16.7220744680851,TRUE,FALSE,FALSE,FALSE,TRUE,2023-05-24,2024-06-09,0,tiiuae/falcon-40b,apache-2.0,2420,40,21.7935839014342 -tiiuae/falcon-40b-instruct_bfloat16_ecb78d97ac356d098e79f0db222c9ce7c5d9ee5f_False,tiiuae/falcon-40b-instruct,ecb78d97ac356d098e79f0db222c9ce7c5d9ee5f,bfloat16,chatmodels,Original,FalconForCausalLM,10.4341543148279,FALSE,IFEval,0.24544874266945,24.544874266945,BBH,0.40538675151592,17.2201142032645,MATH Level 5,0.0166163141993958,1.66163141993958,GPQA,0.25,0,MUSR,0.376229166666667,5.16197916666667,MMLU-PRO,0.226146941489362,14.0163268321513,TRUE,FALSE,FALSE,FALSE,TRUE,2023-05-25,2024-06-09,0,tiiuae/falcon-40b-instruct,apache-2.0,1172,40,19.7332454871768 +tiiuae/falcon-40b_bfloat16_4a70170c215b36a3cce4b4253f6d0612bb7d4146_False,tiiuae/falcon-40b,4a70170c215b36a3cce4b4253f6d0612bb7d4146,bfloat16,pretrained,Original,FalconForCausalLM,11.3635401118469,FALSE,IFEval,0.249645385355302,24.9645385355302,BBH,0.40185324955958,16.5833047303122,MATH Level 5,0.0158610271903323,1.58610271903323,GPQA,0.273489932885906,3.13199105145414,MUSR,0.363145833333333,5.19322916666667,MMLU-PRO,0.250498670212766,16.7220744680851,TRUE,FALSE,FALSE,FALSE,TRUE,2023-05-24,2024-06-09,0,tiiuae/falcon-40b,apache-2.0,2421,40,21.7935839014342 +tiiuae/falcon-40b-instruct_bfloat16_ecb78d97ac356d098e79f0db222c9ce7c5d9ee5f_False,tiiuae/falcon-40b-instruct,ecb78d97ac356d098e79f0db222c9ce7c5d9ee5f,bfloat16,chatmodels,Original,FalconForCausalLM,10.4341543148279,FALSE,IFEval,0.24544874266945,24.544874266945,BBH,0.40538675151592,17.2201142032645,MATH Level 5,0.0166163141993958,1.66163141993958,GPQA,0.25,0,MUSR,0.376229166666667,5.16197916666667,MMLU-PRO,0.226146941489362,14.0163268321513,TRUE,FALSE,FALSE,FALSE,TRUE,2023-05-25,2024-06-09,0,tiiuae/falcon-40b-instruct,apache-2.0,1173,40,19.7332454871768 tiiuae/falcon-7b_bfloat16_898df1396f35e447d5fe44e0a3ccaaaa69f30d36_False,tiiuae/falcon-7b,898df1396f35e447d5fe44e0a3ccaaaa69f30d36,bfloat16,pretrained,Original,FalconForCausalLM,5.11050413623086,FALSE,IFEval,0.182051401392749,18.2051401392749,BBH,0.328524461173222,5.96393691187605,MATH Level 5,0.00604229607250755,0.604229607250755,GPQA,0.24496644295302,0,MUSR,0.37784375,4.49713541666667,MMLU-PRO,0.112533244680851,1.39258274231678,TRUE,FALSE,FALSE,FALSE,TRUE,2023-04-24,2024-06-09,0,tiiuae/falcon-7b,apache-2.0,1080,7,0.785841237420765 tiiuae/falcon-7b-instruct_bfloat16_cf4b3c42ce2fdfe24f753f0f0d179202fea59c99_False,tiiuae/falcon-7b-instruct,cf4b3c42ce2fdfe24f753f0f0d179202fea59c99,bfloat16,chatmodels,Original,FalconForCausalLM,5.01586897414341,FALSE,IFEval,0.196888699761078,19.6888699761078,BBH,0.320342215123558,4.82317846067443,MATH Level 5,0.00604229607250755,0.604229607250755,GPQA,0.24748322147651,0,MUSR,0.363364583333333,3.25390625,MMLU-PRO,0.115525265957447,1.72502955082742,TRUE,FALSE,FALSE,FALSE,TRUE,2023-04-25,2024-06-09,0,tiiuae/falcon-7b-instruct,apache-2.0,930,7,0.766214525605888 tiiuae/falcon-mamba-7b_bfloat16_5337fd73f19847e111ba2291f3f0e1617b90c37d_False,tiiuae/falcon-mamba-7b,5337fd73f19847e111ba2291f3f0e1617b90c37d,bfloat16,pretrained,Original,FalconMambaForCausalLM,15.1162974435226,FALSE,IFEval,0.333576022730799,33.3576022730799,BBH,0.428485498860437,19.8768778035434,MATH Level 5,0.040785498489426,4.0785498489426,GPQA,0.310402684563758,8.05369127516779,MUSR,0.42103125,10.8622395833333,MMLU-PRO,0.230219414893617,14.4688238770686,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-17,2024-07-23,0,tiiuae/falcon-mamba-7b,other,221,7,3.61040791749829 @@ -2092,7 +2092,7 @@ v000000/L3.1-Niitorm-8B-DPO-t0.0001_float16_a34150b5f63de4bc83d79b1de127faff3750 v000000/L3.1-Storniitova-8B_bfloat16_05b126857f43d1b1383e50f8c97d214ceb199723_True,v000000/L3.1-Storniitova-8B,05b126857f43d1b1383e50f8c97d214ceb199723,bfloat16,basemergesandmoerges,Original,LlamaForCausalLM,28.2817068040347,TRUE,IFEval,0.78165600606391,78.1656006063911,BBH,0.515145200431188,30.8109931855899,MATH Level 5,0.146525679758308,14.6525679758308,GPQA,0.289429530201342,5.2572706935123,MUSR,0.402895833333333,9.96197916666666,MMLU-PRO,0.377576462765957,30.8418291962175,FALSE,FALSE,FALSE,FALSE,FALSE,2024-09-12,2024-09-18,1,v000000/L3.1-Storniitova-8B (Merge),"",7,8.03,0.81353999975055 v000000/Qwen2.5-14B-Gutenberg-1e-Delta_bfloat16_f624854b4380e01322e752ce4daadd49ac86580f_True,v000000/Qwen2.5-14B-Gutenberg-1e-Delta,f624854b4380e01322e752ce4daadd49ac86580f,bfloat16,chatmodels,Original,Qwen2ForCausalLM,32.1050963971607,TRUE,IFEval,0.80451202808548,80.451202808548,BBH,0.639849930188539,48.6166718794722,MATH Level 5,0,0,GPQA,0.328859060402685,10.5145413870246,MUSR,0.407302083333333,9.37942708333333,MMLU-PRO,0.493018617021277,43.6687352245863,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-20,2024-09-28,1,v000000/Qwen2.5-14B-Gutenberg-1e-Delta (Merge),apache-2.0,4,14.77,1.80238650719015 v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpeno_bfloat16_1069abb4c25855e67ffaefa08a0befbb376e7ca7_True,v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpeno,1069abb4c25855e67ffaefa08a0befbb376e7ca7,bfloat16,basemergesandmoerges,Original,Qwen2ForCausalLM,32.4876562844531,TRUE,IFEval,0.81974937609986,81.974937609986,BBH,0.639010174859259,48.4521238338806,MATH Level 5,0,0,GPQA,0.331375838926175,10.8501118568233,MUSR,0.411364583333333,10.05390625,MMLU-PRO,0.492353723404255,43.5948581560284,TRUE,TRUE,FALSE,FALSE,FALSE,2024-09-20,2024-12-07,1,v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpeno (Merge),apache-2.0,4,14.77,3.78815502439465 -v000000/Qwen2.5-Lumen-14B_bfloat16_fbb1d184ed01dac52d307737893ebb6b0ace444c_True,v000000/Qwen2.5-Lumen-14B,fbb1d184ed01dac52d307737893ebb6b0ace444c,bfloat16,chatmodels,Original,Qwen2ForCausalLM,32.2002882083385,TRUE,IFEval,0.80636045692097,80.636045692097,BBH,0.639080951114967,48.5078608440576,MATH Level 5,0,0,GPQA,0.328020134228188,10.4026845637584,MUSR,0.411395833333333,10.2911458333333,MMLU-PRO,0.490275930851064,43.3639923167849,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-20,2024-09-20,1,v000000/Qwen2.5-Lumen-14B (Merge),apache-2.0,18,14.77,1.83669254396863 +v000000/Qwen2.5-Lumen-14B_bfloat16_fbb1d184ed01dac52d307737893ebb6b0ace444c_True,v000000/Qwen2.5-Lumen-14B,fbb1d184ed01dac52d307737893ebb6b0ace444c,bfloat16,chatmodels,Original,Qwen2ForCausalLM,32.2002882083385,TRUE,IFEval,0.80636045692097,80.636045692097,BBH,0.639080951114967,48.5078608440576,MATH Level 5,0,0,GPQA,0.328020134228188,10.4026845637584,MUSR,0.411395833333333,10.2911458333333,MMLU-PRO,0.490275930851064,43.3639923167849,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-20,2024-09-20,1,v000000/Qwen2.5-Lumen-14B (Merge),apache-2.0,17,14.77,1.83669254396863 vhab10/Llama-3.1-8B-Base-Instruct-SLERP_bfloat16_eccb4bde0dc91f586954109ecdce7c94f47e2625_False,vhab10/Llama-3.1-8B-Base-Instruct-SLERP,eccb4bde0dc91f586954109ecdce7c94f47e2625,bfloat16,basemergesandmoerges,Original,LlamaForCausalLM,19.2496173143165,FALSE,IFEval,0.290711977552893,29.0711977552893,BBH,0.50574432680708,29.9260416230926,MATH Level 5,0.118580060422961,11.8580060422961,GPQA,0.296140939597315,6.15212527964205,MUSR,0.4010625,9.36614583333333,MMLU-PRO,0.362117686170213,29.1241873522459,TRUE,TRUE,FALSE,FALSE,FALSE,2024-09-16,2024-09-29,1,vhab10/Llama-3.1-8B-Base-Instruct-SLERP (Merge),mit,1,8.03,0.806720781113926 vhab10/Llama-3.2-Instruct-3B-TIES_bfloat16_0e8661730f40a6a279bd273cfe9fe46bbd0507dd_False,vhab10/Llama-3.2-Instruct-3B-TIES,0e8661730f40a6a279bd273cfe9fe46bbd0507dd,bfloat16,basemergesandmoerges,Original,LlamaForCausalLM,17.2965618272248,FALSE,IFEval,0.47273678284729,47.273678284729,BBH,0.433236499665141,19.183159360188,MATH Level 5,0.0959214501510574,9.59214501510574,GPQA,0.269295302013423,2.57270693512304,MUSR,0.34965625,3.87369791666667,MMLU-PRO,0.29155585106383,21.2839834515366,TRUE,TRUE,FALSE,FALSE,FALSE,2024-10-06,2024-11-23,1,vhab10/Llama-3.2-Instruct-3B-TIES (Merge),mit,0,1.848,1.12292646418826 vhab10/llama-3-8b-merged-linear_float16_c37e7671b5ccfadbf3065fa5b48af05cd4f13292_True,vhab10/llama-3-8b-merged-linear,c37e7671b5ccfadbf3065fa5b48af05cd4f13292,float16,basemergesandmoerges,Original,LlamaForCausalLM,23.9113683368941,TRUE,IFEval,0.591663452971449,59.1663452971449,BBH,0.493709374434985,27.8160513277408,MATH Level 5,0.081570996978852,8.1570996978852,GPQA,0.299496644295302,6.59955257270694,MUSR,0.419052083333333,11.6815104166667,MMLU-PRO,0.370428856382979,30.0476507092199,TRUE,FALSE,FALSE,FALSE,FALSE,2024-09-26,2024-09-26,1,vhab10/llama-3-8b-merged-linear (Merge),mit,0,4.65,1.30494333445873 @@ -2205,7 +2205,7 @@ zelk12/MT3-Gen2-gemma-2-9B_bfloat16_e4ef057d20751d89934025e9088ba98d89b921b5_Tru zelk12/MT3-Gen3-gemma-2-9B_bfloat16_4ad54d6295f6364aa87f7aaa2a7bd112fb92ec00_True,zelk12/MT3-Gen3-gemma-2-9B,4ad54d6295f6364aa87f7aaa2a7bd112fb92ec00,bfloat16,basemergesandmoerges,Original,Gemma2ForCausalLM,32.3599943106348,TRUE,IFEval,0.785627690084531,78.5627690084531,BBH,0.60888922159878,43.7837402519492,MATH Level 5,0.0906344410876133,9.06344410876133,GPQA,0.351510067114094,13.5346756152125,MUSR,0.42575,12.51875,MMLU-PRO,0.430269281914894,36.6965868794326,FALSE,FALSE,FALSE,FALSE,FALSE,2024-12-07,2024-12-07,1,zelk12/MT3-Gen3-gemma-2-9B (Merge),"",0,10.159,1.90446256775547 zelk12/MT3-gemma-2-9B_bfloat16_d501b6ea59896fac3dc0a623501a5493b3573cde_True,zelk12/MT3-gemma-2-9B,d501b6ea59896fac3dc0a623501a5493b3573cde,bfloat16,basemergesandmoerges,Original,Gemma2ForCausalLM,32.3525241450138,TRUE,IFEval,0.778608536461035,77.8608536461035,BBH,0.61307842026088,44.2484645159597,MATH Level 5,0.104984894259819,10.4984894259819,GPQA,0.344798657718121,12.6398210290828,MUSR,0.424291666666667,11.903125,MMLU-PRO,0.432679521276596,36.9643912529551,FALSE,FALSE,FALSE,FALSE,FALSE,2024-10-15,2024-10-16,1,zelk12/MT3-gemma-2-9B (Merge),"",1,10.159,3.13665288776858 zelk12/MT4-Gen1-gemma-2-9B_bfloat16_6ed2c66246c7f354decfd3579acb534dc4b0b48c_True,zelk12/MT4-Gen1-gemma-2-9B,6ed2c66246c7f354decfd3579acb534dc4b0b48c,bfloat16,basemergesandmoerges,Original,Gemma2ForCausalLM,33.5449942134774,TRUE,IFEval,0.789499638736331,78.9499638736331,BBH,0.609382799602833,44.0095244503664,MATH Level 5,0.150302114803625,15.0302114803625,GPQA,0.343959731543624,12.5279642058166,MUSR,0.432229166666667,13.0953125,MMLU-PRO,0.43891289893617,37.6569887706856,FALSE,FALSE,FALSE,FALSE,FALSE,2024-10-25,2024-10-29,1,zelk12/MT4-Gen1-gemma-2-9B (Merge),"",0,10.159,2.1035608008152 -zelk12/MT4-Gen2-gemma-2-9B_bfloat16_4d61a5799b11641a24e8b0f3eda0e987ff392089_True,zelk12/MT4-Gen2-gemma-2-9B,4d61a5799b11641a24e8b0f3eda0e987ff392089,bfloat16,basemergesandmoerges,Original,Gemma2ForCausalLM,33.7947321547591,TRUE,IFEval,0.805061680784762,80.5061680784762,BBH,0.610834854397354,44.1766576613372,MATH Level 5,0.157099697885196,15.7099697885196,GPQA,0.345637583892617,12.751677852349,MUSR,0.42565625,12.20703125,MMLU-PRO,0.436751994680851,37.4168882978723,FALSE,FALSE,FALSE,FALSE,FALSE,2024-11-22,2024-11-22,1,zelk12/MT4-Gen2-gemma-2-9B (Merge),"",1,10.159,1.97704726482664 +zelk12/MT4-Gen2-gemma-2-9B_bfloat16_4d61a5799b11641a24e8b0f3eda0e987ff392089_True,zelk12/MT4-Gen2-gemma-2-9B,4d61a5799b11641a24e8b0f3eda0e987ff392089,bfloat16,basemergesandmoerges,Original,Gemma2ForCausalLM,33.7947321547591,TRUE,IFEval,0.805061680784762,80.5061680784762,BBH,0.610834854397354,44.1766576613372,MATH Level 5,0.157099697885196,15.7099697885196,GPQA,0.345637583892617,12.751677852349,MUSR,0.42565625,12.20703125,MMLU-PRO,0.436751994680851,37.4168882978723,FALSE,FALSE,FALSE,FALSE,FALSE,2024-11-22,2024-11-22,1,zelk12/MT4-Gen2-gemma-2-9B (Merge),"",2,10.159,1.97704726482664 zelk12/MT4-Gen3-gemma-2-9B_bfloat16_f93026d28ca1707e8c21620be8558eed6be43b1c_True,zelk12/MT4-Gen3-gemma-2-9B,f93026d28ca1707e8c21620be8558eed6be43b1c,bfloat16,basemergesandmoerges,Original,Gemma2ForCausalLM,33.2397517112983,TRUE,IFEval,0.784054087598683,78.4054087598683,BBH,0.608711288934396,43.8943901025148,MATH Level 5,0.151057401812689,15.1057401812689,GPQA,0.343959731543624,12.5279642058166,MUSR,0.424322916666667,11.9403645833333,MMLU-PRO,0.438081781914894,37.5646424349882,FALSE,FALSE,FALSE,FALSE,FALSE,2024-12-08,2024-12-08,1,zelk12/MT4-Gen3-gemma-2-9B (Merge),"",0,10.159,1.95870126561899 zelk12/MT4-gemma-2-9B_bfloat16_2167ea02baf9145a697a7d828a17c75b86e5e282_True,zelk12/MT4-gemma-2-9B,2167ea02baf9145a697a7d828a17c75b86e5e282,bfloat16,basemergesandmoerges,Original,Gemma2ForCausalLM,33.4473486093193,TRUE,IFEval,0.776160587241852,77.6160587241852,BBH,0.607313601341302,43.5538274995852,MATH Level 5,0.173716012084592,17.3716012084592,GPQA,0.338087248322148,11.744966442953,MUSR,0.430927083333333,12.99921875,MMLU-PRO,0.436585771276596,37.3984190307329,FALSE,FALSE,FALSE,FALSE,FALSE,2024-10-16,2024-10-20,1,zelk12/MT4-gemma-2-9B (Merge),"",0,10.159,3.15525857172439 zelk12/MT5-Gen1-gemma-2-9B_bfloat16_0291b776e80f38381788cd8f1fb2c3435ad891b5_True,zelk12/MT5-Gen1-gemma-2-9B,0291b776e80f38381788cd8f1fb2c3435ad891b5,bfloat16,basemergesandmoerges,Original,Gemma2ForCausalLM,31.8976319819481,TRUE,IFEval,0.783129873180938,78.3129873180938,BBH,0.611047683738306,44.1833346107942,MATH Level 5,0.0687311178247734,6.87311178247734,GPQA,0.347315436241611,12.9753914988814,MUSR,0.420385416666667,11.61484375,MMLU-PRO,0.436835106382979,37.4261229314421,FALSE,FALSE,FALSE,FALSE,FALSE,2024-10-25,2024-10-31,1,zelk12/MT5-Gen1-gemma-2-9B (Merge),"",0,10.159,2.01725286807503 diff --git a/csv/merged.csv b/csv/merged.csv index 62838e6..6d86f4e 100644 --- a/csv/merged.csv +++ b/csv/merged.csv @@ -1,32 +1,32 @@ key,id,model_name,model_sha,model_precision,model_type,model_weight_type,model_architecture,model_average_score,model_has_chat_template,evaluations_ifeval_name,evaluations_ifeval_value,evaluations_ifeval_normalized_score,evaluations_bbh_name,evaluations_bbh_value,evaluations_bbh_normalized_score,evaluations_math_name,evaluations_math_value,evaluations_math_normalized_score,evaluations_gpqa_name,evaluations_gpqa_value,evaluations_gpqa_normalized_score,evaluations_musr_name,evaluations_musr_value,evaluations_musr_normalized_score,evaluations_mmlu_pro_name,evaluations_mmlu_pro_value,evaluations_mmlu_pro_normalized_score,features_is_not_available_on_hub,features_is_merged,features_is_moe,features_is_flagged,features_is_highlighted_by_maintainer,metadata_upload_date,metadata_submission_date,metadata_generation,metadata_base_model,metadata_hub_license,metadata_hub_hearts,metadata_params_billions,metadata_co2_cost,rank,rank_stylectrl,model,arena_score,95_pct_ci,votes,organization,license,knowledge_cutoff,url -aya-expanse-32b,CohereForAI/aya-expanse-32b_float16_08b69cfa4240e2009c80ad304f000b491d1b8c38_True,CohereForAI/aya-expanse-32b,08b69cfa4240e2009c80ad304f000b491d1b8c38,float16,chatmodels,Original,CohereForCausalLM,29.3912190893162,TRUE,IFEval,0.730173716849072,73.0173716849072,BBH,0.564867009921211,38.7096114330142,MATH Level 5,0.13368580060423,13.368580060423,GPQA,0.325503355704698,10.0671140939597,MUSR,0.387270833333333,6.40885416666667,MMLU-PRO,0.41298204787234,34.7757830969267,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-23,2024-10-24,0,CohereForAI/aya-expanse-32b,cc-by-nc-4.0,187,32.296,5.5177350999101,48,57,Aya-Expanse-32B,1208,+4/-5,20332,Cohere,CC-BY-NC-4.0,Unknown,https://huggingface.co/CohereForAI/aya-expanse-32b +aya-expanse-32b,CohereForAI/aya-expanse-32b_float16_08b69cfa4240e2009c80ad304f000b491d1b8c38_True,CohereForAI/aya-expanse-32b,08b69cfa4240e2009c80ad304f000b491d1b8c38,float16,chatmodels,Original,CohereForCausalLM,29.3912190893162,TRUE,IFEval,0.730173716849072,73.0173716849072,BBH,0.564867009921211,38.7096114330142,MATH Level 5,0.13368580060423,13.368580060423,GPQA,0.325503355704698,10.0671140939597,MUSR,0.387270833333333,6.40885416666667,MMLU-PRO,0.41298204787234,34.7757830969267,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-23,2024-10-24,0,CohereForAI/aya-expanse-32b,cc-by-nc-4.0,188,32.296,5.5177350999101,48,57,Aya-Expanse-32B,1208,+4/-5,20332,Cohere,CC-BY-NC-4.0,Unknown,https://huggingface.co/CohereForAI/aya-expanse-32b deepseek-llm-67b-chat,deepseek-ai/deepseek-llm-67b-chat_bfloat16_79648bef7658bb824e4630740f6e1484c1b0620b_True,deepseek-ai/deepseek-llm-67b-chat,79648bef7658bb824e4630740f6e1484c1b0620b,bfloat16,chatmodels,Original,LlamaForCausalLM,26.9959289542937,TRUE,IFEval,0.558715319795919,55.8715319795919,BBH,0.524341617974236,33.2252419253453,MATH Level 5,0.0740181268882175,7.40181268882175,GPQA,0.316275167785235,8.83668903803132,MUSR,0.505864583333333,23.9330729166667,MMLU-PRO,0.394365026595745,32.707225177305,TRUE,FALSE,FALSE,FALSE,TRUE,2023-11-29,2024-06-12,0,deepseek-ai/deepseek-llm-67b-chat,other,177,67,59.8218086686963,118,111,DeepSeek-LLM-67B-Chat,1077,+7/-6,4987,DeepSeek AI,DeepSeek License,2023/11,https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat dolly-v2-12b,databricks/dolly-v2-12b_bfloat16_19308160448536e378e3db21a73a751579ee7fdd_False,databricks/dolly-v2-12b,19308160448536e378e3db21a73a751579ee7fdd,bfloat16,fine-tunedondomain-specificdatasets,Original,GPTNeoXForCausalLM,6.3830238203141,FALSE,IFEval,0.235507342739487,23.5507342739487,BBH,0.331997316737713,6.37789413745296,MATH Level 5,0.0143504531722054,1.43504531722054,GPQA,0.240771812080537,0,MUSR,0.37390625,5.50494791666667,MMLU-PRO,0.112865691489362,1.42952127659574,TRUE,FALSE,FALSE,FALSE,TRUE,2023-04-11,2024-06-12,0,databricks/dolly-v2-12b,mit,1950,12,1.39711946227966,168,166,Dolly-V2-12B,822,+12/-10,3485,Databricks,MIT,2023/4,https://huggingface.co/databricks/dolly-v2-12b gemma-1.1-2b-it,google/gemma-1.1-2b-it_bfloat16_bf4924f313df5166dee1467161e886e55f2eb4d4_True,google/gemma-1.1-2b-it,bf4924f313df5166dee1467161e886e55f2eb4d4,bfloat16,chatmodels,Original,GemmaForCausalLM,7.77643528435205,TRUE,IFEval,0.306748316688608,30.6748316688608,BBH,0.318463497481492,5.86282672277435,MATH Level 5,0.00151057401812689,0.151057401812689,GPQA,0.269295302013423,2.57270693512304,MUSR,0.339395833333333,2.02447916666667,MMLU-PRO,0.148354388297872,5.3727098108747,TRUE,FALSE,FALSE,FALSE,TRUE,2024-03-26,2024-06-12,0,google/gemma-1.1-2b-it,gemma,152,2.506,0.32921478142276,148,140,Gemma-1.1-2b-it,1021,+5/-7,11350,Google,Gemma license,2024/2,https://huggingface.co/google/gemma-1.1-2b-it gemma-1.1-7b-it,google/gemma-1.1-7b-it_bfloat16_16128b0aeb50762ea96430c0c06a37941bf9f274_True,google/gemma-1.1-7b-it,16128b0aeb50762ea96430c0c06a37941bf9f274,bfloat16,chatmodels,Original,GemmaForCausalLM,17.4795862430713,TRUE,IFEval,0.503910734628563,50.3910734628563,BBH,0.393529796283325,15.9342093850132,MATH Level 5,0.0362537764350453,3.62537764350453,GPQA,0.293624161073826,5.8165548098434,MUSR,0.423020833333333,11.5109375,MMLU-PRO,0.258394281914894,17.5993646572104,TRUE,FALSE,FALSE,FALSE,TRUE,2024-03-26,2024-06-12,0,google/gemma-1.1-7b-it,gemma,266,8.538,0.578299189963354,115,107,Gemma-1.1-7B-it,1084,+4/-4,25092,Google,Gemma license,2024/2,https://huggingface.co/google/gemma-1.1-7b-it gemma-2-27b-it,google/gemma-2-27b-it_bfloat16_f6c533e5eb013c7e31fc74ef042ac4f3fb5cf40b_True,google/gemma-2-27b-it,f6c533e5eb013c7e31fc74ef042ac4f3fb5cf40b,bfloat16,chatmodels,Original,Gemma2ForCausalLM,32.3223187688799,TRUE,IFEval,0.797767700811624,79.7767700811624,BBH,0.64513874331688,49.2728421513039,MATH Level 5,0.00755287009063444,0.755287009063444,GPQA,0.375,16.6666666666667,MUSR,0.403302083333333,9.11276041666667,MMLU-PRO,0.445146276595745,38.3495862884161,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-24,2024-08-07,1,google/gemma-2-27b,gemma,463,27.227,4.82621118669274,45,40,Gemma-2-27B-it,1220,+2/-3,65003,Google,Gemma license,2024/6,https://aistudio.google.com/app/prompts/new_chat?model=gemma-2-27b-it -gemma-2-2b-it,google/gemma-2-2b-it_bfloat16_2b6ac3ff954ad896c115bbfa1b571cd93ea2c20f_True,google/gemma-2-2b-it,2b6ac3ff954ad896c115bbfa1b571cd93ea2c20f,bfloat16,fine-tunedondomain-specificdatasets,Original,InternLM2ForCausalLM,17.0469392949665,TRUE,IFEval,0.566833778817981,56.6833778817981,BBH,0.419923089142747,17.9807928815234,MATH Level 5,0.000755287009063444,0.0755287009063444,GPQA,0.274328859060403,3.24384787472036,MUSR,0.392885416666667,7.07734375,MMLU-PRO,0.25498670212766,17.2207446808511,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-16,2024-07-31,1,google/gemma-2-2b,gemma,769,2.614,1.23474327420585,90,101,Gemma-2-2b-it,1141,+3/-4,36399,Google,Gemma license,2024/7,https://aistudio.google.com/app/prompts/new_chat?model=gemma-2-2b-it -gemma-2-9b-it,google/gemma-2-9b-it_bfloat16_1937c70277fcc5f7fb0fc772fc5bc69378996e71_True,google/gemma-2-9b-it,1937c70277fcc5f7fb0fc772fc5bc69378996e71,bfloat16,chatmodels,Original,Gemma2ForCausalLM,28.8627904641512,TRUE,IFEval,0.743562636027961,74.3562636027961,BBH,0.599034250416413,42.1366196836647,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.360738255033557,14.7651006711409,MUSR,0.407270833333333,9.7421875,MMLU-PRO,0.387549867021277,31.9499852245863,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-24,2024-07-11,1,google/gemma-2-9b,gemma,583,9,5.01449702077493,64,61,Gemma-2-9B-it,1190,+4/-3,44837,Google,Gemma license,2024/6,https://aistudio.google.com/app/prompts/new_chat?model=gemma-2-9b-it +gemma-2-2b-it,google/gemma-2-2b-it_bfloat16_2b6ac3ff954ad896c115bbfa1b571cd93ea2c20f_True,google/gemma-2-2b-it,2b6ac3ff954ad896c115bbfa1b571cd93ea2c20f,bfloat16,fine-tunedondomain-specificdatasets,Original,InternLM2ForCausalLM,17.0469392949665,TRUE,IFEval,0.566833778817981,56.6833778817981,BBH,0.419923089142747,17.9807928815234,MATH Level 5,0.000755287009063444,0.0755287009063444,GPQA,0.274328859060403,3.24384787472036,MUSR,0.392885416666667,7.07734375,MMLU-PRO,0.25498670212766,17.2207446808511,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-16,2024-07-31,1,google/gemma-2-2b,gemma,771,2.614,1.23474327420585,90,101,Gemma-2-2b-it,1141,+3/-4,36399,Google,Gemma license,2024/7,https://aistudio.google.com/app/prompts/new_chat?model=gemma-2-2b-it +gemma-2-9b-it,google/gemma-2-9b-it_bfloat16_1937c70277fcc5f7fb0fc772fc5bc69378996e71_True,google/gemma-2-9b-it,1937c70277fcc5f7fb0fc772fc5bc69378996e71,bfloat16,chatmodels,Original,Gemma2ForCausalLM,28.8627904641512,TRUE,IFEval,0.743562636027961,74.3562636027961,BBH,0.599034250416413,42.1366196836647,MATH Level 5,0.00226586102719033,0.226586102719033,GPQA,0.360738255033557,14.7651006711409,MUSR,0.407270833333333,9.7421875,MMLU-PRO,0.387549867021277,31.9499852245863,TRUE,FALSE,FALSE,FALSE,TRUE,2024-06-24,2024-07-11,1,google/gemma-2-9b,gemma,585,9,5.01449702077493,64,61,Gemma-2-9B-it,1190,+4/-3,44837,Google,Gemma license,2024/6,https://aistudio.google.com/app/prompts/new_chat?model=gemma-2-9b-it gemma-2-9b-it-simpo,princeton-nlp/gemma-2-9b-it-SimPO_bfloat16_8c87091f412e3aa6f74f66bd86c57fb81cbc3fde_True,princeton-nlp/gemma-2-9b-it-SimPO,8c87091f412e3aa6f74f66bd86c57fb81cbc3fde,bfloat16,chatmodels,Original,Gemma2ForCausalLM,21.1616516275693,TRUE,IFEval,0.320685780396016,32.0685780396016,BBH,0.583917992316212,40.0934299163717,MATH Level 5,0,0,GPQA,0.335570469798658,11.4093959731544,MUSR,0.412322916666667,10.3403645833333,MMLU-PRO,0.397523271276596,33.0581412529551,TRUE,FALSE,FALSE,FALSE,FALSE,2024-07-16,2024-08-10,2,google/gemma-2-9b,mit,130,9.242,2.76900372425403,45,40,Gemma-2-9B-it-SimPO,1215,+6/-5,10567,Princeton,MIT,2024/7,https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO -gemma-2b-it,google/gemma-2b-it_bfloat16_de144fb2268dee1066f515465df532c05e699d48_True,google/gemma-2b-it,de144fb2268dee1066f515465df532c05e699d48,bfloat16,chatmodels,Original,GemmaForCausalLM,7.22145367714292,TRUE,IFEval,0.269029508371122,26.9029508371122,BBH,0.315081919887885,5.21430302216362,MATH Level 5,0.00453172205438067,0.453172205438067,GPQA,0.278523489932886,3.80313199105145,MUSR,0.334125,3.03229166666667,MMLU-PRO,0.13530585106383,3.92287234042553,TRUE,FALSE,FALSE,FALSE,TRUE,2024-02-08,2024-06-12,0,google/gemma-2b-it,gemma,683,2.506,0.352950331047759,155,154,Gemma-2B-it,989,+7/-8,4924,Google,Gemma license,2024/2,https://huggingface.co/google/gemma-2b-it -gemma-7b-it,google/gemma-7b-it_bfloat16_18329f019fb74ca4b24f97371785268543d687d2_True,google/gemma-7b-it,18329f019fb74ca4b24f97371785268543d687d2,bfloat16,chatmodels,Original,GemmaForCausalLM,12.8681419014102,TRUE,IFEval,0.386832493339894,38.6832493339894,BBH,0.364558292227017,11.8800913445494,MATH Level 5,0.0181268882175227,1.81268882175227,GPQA,0.284395973154362,4.58612975391499,MUSR,0.427427083333333,12.5283854166667,MMLU-PRO,0.169464760638298,7.71830673758865,TRUE,FALSE,FALSE,FALSE,TRUE,2024-02-13,2024-06-12,1,google/gemma-7b,gemma,1139,8.538,1.0999544452693,138,135,Gemma-7B-it,1038,+6/-5,9183,Google,Gemma license,2024/2,https://huggingface.co/google/gemma-7b-it +gemma-2b-it,google/gemma-2b-it_bfloat16_de144fb2268dee1066f515465df532c05e699d48_True,google/gemma-2b-it,de144fb2268dee1066f515465df532c05e699d48,bfloat16,chatmodels,Original,GemmaForCausalLM,7.22145367714292,TRUE,IFEval,0.269029508371122,26.9029508371122,BBH,0.315081919887885,5.21430302216362,MATH Level 5,0.00453172205438067,0.453172205438067,GPQA,0.278523489932886,3.80313199105145,MUSR,0.334125,3.03229166666667,MMLU-PRO,0.13530585106383,3.92287234042553,TRUE,FALSE,FALSE,FALSE,TRUE,2024-02-08,2024-06-12,0,google/gemma-2b-it,gemma,684,2.506,0.352950331047759,155,154,Gemma-2B-it,989,+7/-8,4924,Google,Gemma license,2024/2,https://huggingface.co/google/gemma-2b-it +gemma-7b-it,google/gemma-7b-it_bfloat16_18329f019fb74ca4b24f97371785268543d687d2_True,google/gemma-7b-it,18329f019fb74ca4b24f97371785268543d687d2,bfloat16,chatmodels,Original,GemmaForCausalLM,12.8681419014102,TRUE,IFEval,0.386832493339894,38.6832493339894,BBH,0.364558292227017,11.8800913445494,MATH Level 5,0.0181268882175227,1.81268882175227,GPQA,0.284395973154362,4.58612975391499,MUSR,0.427427083333333,12.5283854166667,MMLU-PRO,0.169464760638298,7.71830673758865,TRUE,FALSE,FALSE,FALSE,TRUE,2024-02-13,2024-06-12,1,google/gemma-7b,gemma,1140,8.538,1.0999544452693,138,135,Gemma-7B-it,1038,+6/-5,9183,Google,Gemma license,2024/2,https://huggingface.co/google/gemma-7b-it granite-3.0-2b-instruct,ibm-granite/granite-3.0-2b-instruct_bfloat16_342f92f4a0b4d6d83c0b61dc6c122e253a4efebd_True,ibm-granite/granite-3.0-2b-instruct,342f92f4a0b4d6d83c0b61dc6c122e253a4efebd,bfloat16,chatmodels,Original,GraniteForCausalLM,18.3205664133779,TRUE,IFEval,0.513977357854936,51.3977357854936,BBH,0.441197720626303,21.7378914109024,MATH Level 5,0.0876132930513595,8.76132930513595,GPQA,0.299496644295302,6.59955257270694,MUSR,0.351489583333333,1.26953125,MMLU-PRO,0.281416223404255,20.1573581560284,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-02,"",1,ibm-granite/granite-3.0-2b-instruct (Merge),apache-2.0,45,2.634,1.01894808156813,119,117,Granite-3.0-2B-Instruct,1074,+8/-7,7247,IBM,Apache 2.0,Unknown,https://huggingface.co/ibm-granite/granite-3.0-2b-instruct granite-3.0-8b-instruct,ibm-granite/granite-3.0-8b-instruct_bfloat16_e0a466fb25b9e07e9c2dc93380a360189700d1f8_True,ibm-granite/granite-3.0-8b-instruct,e0a466fb25b9e07e9c2dc93380a360189700d1f8,bfloat16,chatmodels,Original,GraniteForCausalLM,23.8640332348529,TRUE,IFEval,0.530963399335984,53.0963399335984,BBH,0.519187463184023,31.5881590647151,MATH Level 5,0.132175226586103,13.2175226586103,GPQA,0.332214765100671,10.9619686800895,MUSR,0.3900625,7.02447916666667,MMLU-PRO,0.345661569148936,27.2957299054374,TRUE,FALSE,FALSE,FALSE,TRUE,2024-10-02,2024-10-20,1,ibm-granite/granite-3.0-8b-instruct (Merge),apache-2.0,191,8.171,1.7129925870079,107,101,Granite-3.0-8B-Instruct,1094,+7/-6,7070,IBM,Apache 2.0,Unknown,https://huggingface.co/ibm-granite/granite-3.0-8b-instruct llama-13b,huggyllama/llama-13b_float16_bf57045473f207bb1de1ed035ace226f4d9f9bba_False,huggyllama/llama-13b,bf57045473f207bb1de1ed035ace226f4d9f9bba,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,9.29147946431344,FALSE,IFEval,0.241052629245956,24.1052629245956,BBH,0.398789255811746,16.1457073769258,MATH Level 5,0.0143504531722054,1.43504531722054,GPQA,0.25503355704698,0.671140939597318,MUSR,0.34621875,2.81067708333333,MMLU-PRO,0.195229388297872,10.581043144208,TRUE,FALSE,FALSE,FALSE,FALSE,2023-04-03,2024-07-04,0,huggyllama/llama-13b,other,138,13.016,1.1061405985716,169,168,LLaMA-13B,800,+15/-12,2445,Meta,Non-commercial,2023/2,https://arxiv.org/abs/2302.13971 llama-3-8b-instruct,AI-Sweden-Models/Llama-3-8B-instruct_bfloat16_4e1c955228bdb4d69c1c4560e8d5872312a8f033_True,AI-Sweden-Models/Llama-3-8B-instruct,4e1c955228bdb4d69c1c4560e8d5872312a8f033,bfloat16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,13.7772044149452,TRUE,IFEval,0.240128414828211,24.0128414828211,BBH,0.41734601545153,18.3880956150275,MATH Level 5,0.00453172205438067,0.453172205438067,GPQA,0.265939597315436,2.12527964205817,MUSR,0.47709375,19.93671875,MMLU-PRO,0.259724069148936,17.7471187943262,TRUE,FALSE,FALSE,FALSE,FALSE,2024-06-01,2024-06-27,2,meta-llama/Meta-Llama-3-8B,llama3,10,8.03,1.16611088086752,80,83,Llama-3-8B-Instruct,1152,+2/-2,109304,Meta,Llama 3 Community,2023/3,https://llama.meta.com/llama3/ meta-llama-3.1-70b-instruct,meta-llama/Meta-Llama-3.1-70B-Instruct_bfloat16_b9461463b511ed3c0762467538ea32cf7c9669f2_True,meta-llama/Meta-Llama-3.1-70B-Instruct,b9461463b511ed3c0762467538ea32cf7c9669f2,bfloat16,chatmodels,Original,LlamaForCausalLM,42.1763127975088,TRUE,IFEval,0.866885419575615,86.6885419575615,BBH,0.691728745366365,55.9279917389847,MATH Level 5,0.306646525679758,30.6646525679758,GPQA,0.356543624161074,14.2058165548098,MUSR,0.4580625,17.6911458333333,MMLU-PRO,0.530917553191489,47.8797281323877,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-16,2024-08-15,1,meta-llama/Meta-Llama-3.1-70B,llama3.1,748,70.554,26.8020157168701,32,37,Meta-Llama-3.1-70B-Instruct,1248,+3/-4,55626,Meta,Llama 3.1 Community,2023/12,https://ai.meta.com/blog/meta-llama-3-1/ -meta-llama-3.1-8b-instruct,meta-llama/Meta-Llama-3.1-8B-Instruct_bfloat16_df34336b42332c6d360959e259cd6271c6a09fd4_True,meta-llama/Meta-Llama-3.1-8B-Instruct,df34336b42332c6d360959e259cd6271c6a09fd4,bfloat16,chatmodels,Original,LlamaForCausalLM,28.2044584981019,TRUE,IFEval,0.785577822400121,78.5577822400121,BBH,0.507326783896146,29.8927563524528,MATH Level 5,0.193353474320242,19.3353474320242,GPQA,0.26761744966443,2.3489932885906,MUSR,0.386989583333333,8.40703125,MMLU-PRO,0.376163563829787,30.6848404255319,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-18,2024-08-15,1,meta-llama/Meta-Llama-3.1-8B,llama3.1,3258,8.03,2.48701186834409,70,91,Meta-Llama-3.1-8B-Instruct,1175,+3/-4,50651,Meta,Llama 3.1 Community,2023/12,https://ai.meta.com/blog/meta-llama-3-1/ +meta-llama-3.1-8b-instruct,meta-llama/Meta-Llama-3.1-8B-Instruct_bfloat16_df34336b42332c6d360959e259cd6271c6a09fd4_True,meta-llama/Meta-Llama-3.1-8B-Instruct,df34336b42332c6d360959e259cd6271c6a09fd4,bfloat16,chatmodels,Original,LlamaForCausalLM,28.2044584981019,TRUE,IFEval,0.785577822400121,78.5577822400121,BBH,0.507326783896146,29.8927563524528,MATH Level 5,0.193353474320242,19.3353474320242,GPQA,0.26761744966443,2.3489932885906,MUSR,0.386989583333333,8.40703125,MMLU-PRO,0.376163563829787,30.6848404255319,TRUE,FALSE,FALSE,FALSE,TRUE,2024-07-18,2024-08-15,1,meta-llama/Meta-Llama-3.1-8B,llama3.1,3261,8.03,2.48701186834409,70,91,Meta-Llama-3.1-8B-Instruct,1175,+3/-4,50651,Meta,Llama 3.1 Community,2023/12,https://ai.meta.com/blog/meta-llama-3-1/ mistral-7b-instruct-v0.1,mistralai/Mistral-7B-Instruct-v0.1_bfloat16_73068f3702d050a2fd5aa2ca1e612e5036429398_True,mistralai/Mistral-7B-Instruct-v0.1,73068f3702d050a2fd5aa2ca1e612e5036429398,bfloat16,chatmodels,Original,MistralForCausalLM,12.6957006941243,TRUE,IFEval,0.448706099815157,44.8706099815157,BBH,0.33548084759811,7.64702053582754,MATH Level 5,0.0181268882175227,1.81268882175227,GPQA,0.25,0,MUSR,0.384760416666667,6.12838541666667,MMLU-PRO,0.241439494680851,15.7154994089835,TRUE,FALSE,FALSE,FALSE,TRUE,2023-09-27,2024-06-27,1,mistralai/Mistral-7B-v0.1,apache-2.0,1537,7.242,1.21604471748007,150,149,Mistral-7B-Instruct-v0.1,1008,+9/-5,9145,Mistral,Apache 2.0,2023/9,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1 -mistral-7b-instruct-v0.2,mistralai/Mistral-7B-Instruct-v0.2_bfloat16_41b61a33a2483885c981aa79e0df6b32407ed873_True,mistralai/Mistral-7B-Instruct-v0.2,41b61a33a2483885c981aa79e0df6b32407ed873,bfloat16,chatmodels,Original,MistralForCausalLM,18.4575391254667,TRUE,IFEval,0.549622778671702,54.9622778671702,BBH,0.445973552032928,22.9106019367136,MATH Level 5,0.027190332326284,2.7190332326284,GPQA,0.276006711409396,3.4675615212528,MUSR,0.396604166666667,7.60885416666667,MMLU-PRO,0.271692154255319,19.0769060283688,TRUE,FALSE,FALSE,FALSE,TRUE,2023-12-11,2024-06-12,0,mistralai/Mistral-7B-Instruct-v0.2,apache-2.0,2591,7.242,0.534406629050985,120,125,Mistral-7B-Instruct-v0.2,1072,+4/-4,20074,Mistral,Apache-2.0,2023/12,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2 +mistral-7b-instruct-v0.2,mistralai/Mistral-7B-Instruct-v0.2_bfloat16_41b61a33a2483885c981aa79e0df6b32407ed873_True,mistralai/Mistral-7B-Instruct-v0.2,41b61a33a2483885c981aa79e0df6b32407ed873,bfloat16,chatmodels,Original,MistralForCausalLM,18.4575391254667,TRUE,IFEval,0.549622778671702,54.9622778671702,BBH,0.445973552032928,22.9106019367136,MATH Level 5,0.027190332326284,2.7190332326284,GPQA,0.276006711409396,3.4675615212528,MUSR,0.396604166666667,7.60885416666667,MMLU-PRO,0.271692154255319,19.0769060283688,TRUE,FALSE,FALSE,FALSE,TRUE,2023-12-11,2024-06-12,0,mistralai/Mistral-7B-Instruct-v0.2,apache-2.0,2593,7.242,0.534406629050985,120,125,Mistral-7B-Instruct-v0.2,1072,+4/-4,20074,Mistral,Apache-2.0,2023/12,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2 mixtral-8x22b-instruct-v0.1,mistralai/Mixtral-8x22B-Instruct-v0.1_bfloat16_b0c3516041d014f640267b14feb4e9a84c8e8c71_True,mistralai/Mixtral-8x22B-Instruct-v0.1,b0c3516041d014f640267b14feb4e9a84c8e8c71,bfloat16,chatmodels,Original,MixtralForCausalLM,33.885680288082,TRUE,IFEval,0.718358400156031,71.8358400156031,BBH,0.612492492627202,44.1143455872484,MATH Level 5,0.187311178247734,18.7311178247734,GPQA,0.373322147651007,16.4429530201342,MUSR,0.431114583333333,13.4893229166667,MMLU-PRO,0.448304521276596,38.7005023640662,TRUE,FALSE,TRUE,FALSE,TRUE,2024-04-16,2024-06-12,1,mistralai/Mixtral-8x22B-v0.1,apache-2.0,695,140.621,47.147578592378,83,78,Mixtral-8x22b-Instruct-v0.1,1147,+3/-3,53824,Mistral,Apache 2.0,2024/4,https://mistral.ai/news/mixtral-8x22b/ mixtral-8x7b-instruct-v0.1,mistralai/Mixtral-8x7B-Instruct-v0.1_bfloat16_1e637f2d7cb0a9d6fb1922f305cb784995190a83_True,mistralai/Mixtral-8x7B-Instruct-v0.1,1e637f2d7cb0a9d6fb1922f305cb784995190a83,bfloat16,chatmodels,Original,MixtralForCausalLM,23.8422789394817,TRUE,IFEval,0.559914360563305,55.9914360563305,BBH,0.496236540133565,29.7423983809673,MATH Level 5,0.0929003021148036,9.29003021148036,GPQA,0.302852348993289,7.04697986577182,MUSR,0.420322916666667,11.0736979166667,MMLU-PRO,0.369182180851064,29.9091312056738,TRUE,FALSE,TRUE,FALSE,TRUE,2023-12-10,2024-06-12,1,mistralai/Mixtral-8x7B-v0.1,apache-2.0,4223,46.703,13.7649393661468,100,101,Mixtral-8x7B-Instruct-v0.1,1114,+0/-0,76150,Mistral,Apache 2.0,2023/12,https://mistral.ai/news/mixtral-of-experts/ nous-hermes-2-mixtral-8x7b-dpo,NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO_bfloat16_286ae6737d048ad1d965c2e830864df02db50f2f_True,NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO,286ae6737d048ad1d965c2e830864df02db50f2f,bfloat16,chatmodels,Original,MixtralForCausalLM,27.290249854483,TRUE,IFEval,0.58968980083955,58.968980083955,BBH,0.553885138403382,37.1077837913399,MATH Level 5,0.118580060422961,11.8580060422961,GPQA,0.321308724832215,9.50782997762864,MUSR,0.459541666666667,16.6760416666667,MMLU-PRO,0.366605718085106,29.6228575650118,TRUE,FALSE,TRUE,FALSE,TRUE,2024-01-11,2024-07-27,1,mistralai/Mixtral-8x7B-v0.1,apache-2.0,420,46.703,12.8651437241499,112,122,Nous-Hermes-2-Mixtral-8x7B-DPO,1084,+10/-9,3835,NousResearch,Apache-2.0,2024/1,https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO openchat-3.5-0106,openchat/openchat-3.5-0106_bfloat16_ff058fda49726ecf4ea53dc1635f917cdb8ba36b_True,openchat/openchat-3.5-0106,ff058fda49726ecf4ea53dc1635f917cdb8ba36b,bfloat16,fine-tunedondomain-specificdatasets,Original,MistralForCausalLM,22.6586834330757,TRUE,IFEval,0.595135351977198,59.5135351977198,BBH,0.461697870839606,24.0387112139116,MATH Level 5,0.074773413897281,7.4773413897281,GPQA,0.307885906040268,7.71812080536913,MUSR,0.4254375,11.7463541666667,MMLU-PRO,0.329122340425532,25.4580378250591,TRUE,FALSE,FALSE,FALSE,TRUE,2024-01-07,2024-06-27,1,mistralai/Mistral-7B-v0.1,apache-2.0,348,7.242,2.35495886433684,112,107,OpenChat-3.5-0106,1091,+4/-6,12992,OpenChat,Apache-2.0,2024/1,https://huggingface.co/openchat/openchat-3.5-0106 openhermes-2.5-mistral-7b,teknium/OpenHermes-2.5-Mistral-7B_bfloat16_24c0bea14d53e6f67f1fbe2eca5bfe7cae389b33_True,teknium/OpenHermes-2.5-Mistral-7B,24c0bea14d53e6f67f1fbe2eca5bfe7cae389b33,bfloat16,chatmodels,Original,MistralForCausalLM,21.2668365601522,TRUE,IFEval,0.557141717310071,55.7141717310071,BBH,0.487001325992498,27.7700263678076,MATH Level 5,0.047583081570997,4.7583081570997,GPQA,0.283557046979866,4.47427293064877,MUSR,0.424197916666667,12.0580729166667,MMLU-PRO,0.305435505319149,22.8261672576832,TRUE,FALSE,FALSE,FALSE,TRUE,2023-10-29,2024-06-12,1,mistralai/Mistral-7B-v0.1,apache-2.0,817,7.242,0.472783300310566,119,111,OpenHermes-2.5-Mistral-7B,1074,+7/-7,5091,NousResearch,Apache-2.0,2023/11,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B phi-3-medium-4k-instruct,microsoft/Phi-3-medium-4k-instruct_bfloat16_d194e4e74ffad5a5e193e26af25bcfc80c7f1ffc_True,microsoft/Phi-3-medium-4k-instruct,d194e4e74ffad5a5e193e26af25bcfc80c7f1ffc,bfloat16,chatmodels,Original,Phi3ForCausalLM,32.8962495702928,TRUE,IFEval,0.642271395452954,64.2271395452954,BBH,0.641246489055555,49.3806100742202,MATH Level 5,0.183534743202417,18.3534743202417,GPQA,0.336409395973154,11.5212527964206,MUSR,0.42575,13.0520833333333,MMLU-PRO,0.467586436170213,40.8429373522459,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-07,2024-06-12,0,microsoft/Phi-3-medium-4k-instruct,mit,211,13.96,1.45526252332937,94,100,Phi-3-Medium-4k-Instruct,1123,+4/-4,26126,Microsoft,MIT,2023/10,https://huggingface.co/microsoft/Phi-3-medium-4k-instruct -phi-3-mini-128k-instruct,microsoft/Phi-3-mini-128k-instruct_bfloat16_5be6479b4bc06a081e8f4c6ece294241ccd32dec_True,microsoft/Phi-3-mini-128k-instruct,5be6479b4bc06a081e8f4c6ece294241ccd32dec,bfloat16,chatmodels,Original,Phi3ForCausalLM,25.6262872732554,TRUE,IFEval,0.597633168880792,59.7633168880792,BBH,0.557453179267985,37.0997666322403,MATH Level 5,0.0974320241691843,9.74320241691843,GPQA,0.317953020134228,9.06040268456376,MUSR,0.3936875,7.7109375,MMLU-PRO,0.373420877659575,30.3800975177305,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-22,2024-08-21,0,microsoft/Phi-3-mini-128k-instruct,mit,1610,3.821,24.2222515926888,138,135,Phi-3-Mini-128k-Instruct,1037,+4/-5,21639,Microsoft,MIT,2023/10,https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms/ -phi-3-mini-4k-instruct,microsoft/Phi-3-mini-4k-instruct_bfloat16_ff07dc01615f8113924aed013115ab2abd32115b_True,microsoft/Phi-3-mini-4k-instruct,ff07dc01615f8113924aed013115ab2abd32115b,bfloat16,chatmodels,Original,Phi3ForCausalLM,25.9677326380416,TRUE,IFEval,0.561288492311511,56.1288492311511,BBH,0.567597262633488,39.2693352377728,MATH Level 5,0.11631419939577,11.631419939577,GPQA,0.319630872483222,9.2841163310962,MUSR,0.395020833333333,7.64427083333334,MMLU-PRO,0.386635638297872,31.8484042553192,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-22,2024-06-12,0,microsoft/Phi-3-mini-4k-instruct,mit,1087,3.821,0.804074829912372,124,130,Phi-3-Mini-4k-Instruct,1066,+5/-4,21108,Microsoft,MIT,2023/10,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct -phi-3-mini-4k-instruct,microsoft/Phi-3-mini-4k-instruct_float16_c1358f8a35e6d2af81890deffbbfa575b978c62f_True,microsoft/Phi-3-mini-4k-instruct,c1358f8a35e6d2af81890deffbbfa575b978c62f,float16,chatmodels,Original,Phi3ForCausalLM,27.4111166417796,TRUE,IFEval,0.547674614467391,54.7674614467391,BBH,0.549071891949582,36.5598553051879,MATH Level 5,0.154833836858006,15.4833836858006,GPQA,0.332214765100671,10.9619686800895,MUSR,0.428416666666667,13.11875,MMLU-PRO,0.402177526595745,33.5752807328605,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-22,2024-07-02,0,microsoft/Phi-3-mini-4k-instruct,mit,1087,3.821,0.786699265454341,124,130,Phi-3-Mini-4k-Instruct,1066,+5/-4,21108,Microsoft,MIT,2023/10,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct +phi-3-mini-128k-instruct,microsoft/Phi-3-mini-128k-instruct_bfloat16_5be6479b4bc06a081e8f4c6ece294241ccd32dec_True,microsoft/Phi-3-mini-128k-instruct,5be6479b4bc06a081e8f4c6ece294241ccd32dec,bfloat16,chatmodels,Original,Phi3ForCausalLM,25.6262872732554,TRUE,IFEval,0.597633168880792,59.7633168880792,BBH,0.557453179267985,37.0997666322403,MATH Level 5,0.0974320241691843,9.74320241691843,GPQA,0.317953020134228,9.06040268456376,MUSR,0.3936875,7.7109375,MMLU-PRO,0.373420877659575,30.3800975177305,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-22,2024-08-21,0,microsoft/Phi-3-mini-128k-instruct,mit,1611,3.821,24.2222515926888,138,135,Phi-3-Mini-128k-Instruct,1037,+4/-5,21639,Microsoft,MIT,2023/10,https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms/ +phi-3-mini-4k-instruct,microsoft/Phi-3-mini-4k-instruct_bfloat16_ff07dc01615f8113924aed013115ab2abd32115b_True,microsoft/Phi-3-mini-4k-instruct,ff07dc01615f8113924aed013115ab2abd32115b,bfloat16,chatmodels,Original,Phi3ForCausalLM,25.9677326380416,TRUE,IFEval,0.561288492311511,56.1288492311511,BBH,0.567597262633488,39.2693352377728,MATH Level 5,0.11631419939577,11.631419939577,GPQA,0.319630872483222,9.2841163310962,MUSR,0.395020833333333,7.64427083333334,MMLU-PRO,0.386635638297872,31.8484042553192,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-22,2024-06-12,0,microsoft/Phi-3-mini-4k-instruct,mit,1088,3.821,0.804074829912372,124,130,Phi-3-Mini-4k-Instruct,1066,+5/-4,21108,Microsoft,MIT,2023/10,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct +phi-3-mini-4k-instruct,microsoft/Phi-3-mini-4k-instruct_float16_c1358f8a35e6d2af81890deffbbfa575b978c62f_True,microsoft/Phi-3-mini-4k-instruct,c1358f8a35e6d2af81890deffbbfa575b978c62f,float16,chatmodels,Original,Phi3ForCausalLM,27.4111166417796,TRUE,IFEval,0.547674614467391,54.7674614467391,BBH,0.549071891949582,36.5598553051879,MATH Level 5,0.154833836858006,15.4833836858006,GPQA,0.332214765100671,10.9619686800895,MUSR,0.428416666666667,13.11875,MMLU-PRO,0.402177526595745,33.5752807328605,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-22,2024-07-02,0,microsoft/Phi-3-mini-4k-instruct,mit,1088,3.821,0.786699265454341,124,130,Phi-3-Mini-4k-Instruct,1066,+5/-4,21108,Microsoft,MIT,2023/10,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct phi-3-mini-4k-instruct,unsloth/Phi-3-mini-4k-instruct_float16_636c707430a5509c80b1aa51d05c127ed339a975_True,unsloth/Phi-3-mini-4k-instruct,636c707430a5509c80b1aa51d05c127ed339a975,float16,basemergesandmoerges,Original,MistralForCausalLM,27.1783743374799,TRUE,IFEval,0.544027624480822,54.4027624480822,BBH,0.550023946744103,36.732473265614,MATH Level 5,0.154078549848943,15.4078549848943,GPQA,0.322986577181208,9.73154362416107,MUSR,0.428416666666667,13.11875,MMLU-PRO,0.403091755319149,33.6768617021277,TRUE,FALSE,FALSE,FALSE,FALSE,2024-04-29,2024-11-25,0,unsloth/Phi-3-mini-4k-instruct,mit,41,3.821,0.469533108024419,124,130,Phi-3-Mini-4k-Instruct,1066,+5/-4,21108,Microsoft,MIT,2023/10,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct phi-3-small-8k-instruct,microsoft/Phi-3-small-8k-instruct_bfloat16_1535ae26fb4faada95c6950e8bc6e867cdad6b00_True,microsoft/Phi-3-small-8k-instruct,1535ae26fb4faada95c6950e8bc6e867cdad6b00,bfloat16,chatmodels,Original,Phi3SmallForCausalLM,29.6709218521057,TRUE,IFEval,0.649665110794913,64.9665110794913,BBH,0.620836488087056,46.2055703663891,MATH Level 5,0.0284301430770108,2.84301430770108,GPQA,0.312080536912752,8.27740492170022,MUSR,0.455791666666667,16.7739583333333,MMLU-PRO,0.45063164893617,38.9590721040189,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-07,2024-06-13,0,microsoft/Phi-3-small-8k-instruct,mit,159,7.392,1.0254536035218,103,108,Phi-3-Small-8k-Instruct,1102,+5/-4,18493,Microsoft,MIT,2023/10,https://huggingface.co/microsoft/Phi-3-small-8k-instruct qwen1.5-110b-chat,Qwen/Qwen1.5-110B-Chat_bfloat16_85f86cec25901f2dbd870a86e06756903c9a876a_True,Qwen/Qwen1.5-110B-Chat,85f86cec25901f2dbd870a86e06756903c9a876a,bfloat16,chatmodels,Original,Qwen2ForCausalLM,29.2248366843256,TRUE,IFEval,0.593886443525402,59.3886443525402,BBH,0.618380038558863,44.9845452561663,MATH Level 5,0,0,GPQA,0.341442953020134,12.1923937360179,MUSR,0.452166666666667,16.2875,MMLU-PRO,0.482463430851064,42.4959367612293,TRUE,FALSE,FALSE,FALSE,TRUE,2024-04-25,2024-06-12,0,Qwen/Qwen1.5-110B-Chat,other,123,111.21,72.5652930561157,77,73,Qwen1.5-110B-Chat,1162,+4/-4,27478,Alibaba,Qianwen LICENSE,2024/4,https://qwenlm.github.io/blog/qwen1.5-110b/ @@ -35,8 +35,8 @@ qwen1.5-32b-chat,Qwen/Qwen1.5-32B-Chat_bfloat16_0997b012af6ddd5465d40465a8415535 qwen1.5-4b-chat,Qwen/Qwen1.5-4B-Chat_bfloat16_a7a4d4945d28bac955554c9abd2f74a71ebbf22f_True,Qwen/Qwen1.5-4B-Chat,a7a4d4945d28bac955554c9abd2f74a71ebbf22f,bfloat16,chatmodels,Original,Qwen2ForCausalLM,12.3377534239841,TRUE,IFEval,0.315665766832006,31.5665766832006,BBH,0.400554856114861,16.2970785289083,MATH Level 5,0.0105740181268882,1.05740181268882,GPQA,0.266778523489933,2.23713646532438,MUSR,0.39778125,7.35598958333333,MMLU-PRO,0.239611037234043,15.5123374704492,TRUE,FALSE,FALSE,FALSE,TRUE,2024-01-30,2024-06-12,0,Qwen/Qwen1.5-4B-Chat,other,38,3.95,0.866150647838799,156,151,Qwen1.5-4B-Chat,988,+7/-6,7813,Alibaba,Qianwen LICENSE,2024/2,https://qwenlm.github.io/blog/qwen1.5/ qwen1.5-7b-chat,Qwen/Qwen1.5-7B-Chat_bfloat16_5f4f5e69ac7f1d508f8369e977de208b4803444b_True,Qwen/Qwen1.5-7B-Chat,5f4f5e69ac7f1d508f8369e977de208b4803444b,bfloat16,chatmodels,Original,Qwen2ForCausalLM,16.5761729315825,TRUE,IFEval,0.437115741787347,43.7115741787347,BBH,0.451005311652135,22.3791295999528,MATH Level 5,0,0,GPQA,0.302852348993289,7.04697986577182,MUSR,0.37790625,4.63828125,MMLU-PRO,0.295129654255319,21.6810726950355,TRUE,FALSE,FALSE,FALSE,TRUE,2024-01-30,2024-06-12,0,Qwen/Qwen1.5-7B-Chat,other,164,7.721,1.07882659669136,120,125,Qwen1.5-7B-Chat,1070,+8/-8,4868,Alibaba,Qianwen LICENSE,2024/2,https://qwenlm.github.io/blog/qwen1.5/ qwen2-72b-instruct,Qwen/Qwen2-72B-Instruct_bfloat16_1af63c698f59c4235668ec9c1395468cb7cd7e79_False,Qwen/Qwen2-72B-Instruct,1af63c698f59c4235668ec9c1395468cb7cd7e79,bfloat16,chatmodels,Original,Qwen2ForCausalLM,42.9143041555209,FALSE,IFEval,0.7989168738946,79.89168738946,BBH,0.697730968386067,57.483009118763,MATH Level 5,0.376888217522659,37.6888217522659,GPQA,0.37248322147651,16.331096196868,MUSR,0.456010416666667,17.16796875,MMLU-PRO,0.540309175531915,48.9232417257683,TRUE,FALSE,FALSE,FALSE,TRUE,2024-05-28,2024-06-26,1,Qwen/Qwen2-72B,other,684,72.706,37.5539744227,64,58,Qwen2-72B-Instruct,1187,+4/-4,38954,Alibaba,Qianwen LICENSE,2024/6,https://qwenlm.github.io/blog/qwen2/ -qwen2.5-72b-instruct,Qwen/Qwen2.5-72B-Instruct_bfloat16_a13fff9ad76700c7ecff2769f75943ba8395b4a7_True,Qwen/Qwen2.5-72B-Instruct,a13fff9ad76700c7ecff2769f75943ba8395b4a7,bfloat16,chatmodels,Original,Qwen2ForCausalLM,38.2120812616148,TRUE,IFEval,0.863837949972739,86.3837949972739,BBH,0.727274732174482,61.8732556687879,MATH Level 5,0.0120845921450151,1.20845921450151,GPQA,0.375,16.6666666666667,MUSR,0.420604166666667,11.7421875,MMLU-PRO,0.562583111702128,51.3981235224587,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-10-16,1,Qwen/Qwen2.5-72B,other,591,72.706,33.0067683243991,25,31,Qwen2.5-72B-Instruct,1258,+3/-3,33591,Alibaba,Qwen,2024/9,https://qwenlm.github.io/blog/qwen2.5/ -qwen2.5-coder-32b-instruct,Qwen/Qwen2.5-Coder-32B-Instruct_float16_b47205940b83b5b484577359f71ee7b88472df67_False,Qwen/Qwen2.5-Coder-32B-Instruct,b47205940b83b5b484577359f71ee7b88472df67,float16,chatmodels,Original,Qwen2ForCausalLM,38.7525412608276,FALSE,IFEval,0.726526726862503,72.6526726862503,BBH,0.662522222240513,52.2665152094361,MATH Level 5,0.427492447129909,42.7492447129909,GPQA,0.348993288590604,13.1991051454139,MUSR,0.438583333333333,13.7229166666667,MMLU-PRO,0.441323138297872,37.924793144208,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-06,2024-12-10,1,Qwen/Qwen2.5-Coder-32B-Instruct (Merge),apache-2.0,1294,32,4.69438966297979,43,49,Qwen2.5-Coder-32B-Instruct,1217,+7/-8,5748,Alibaba,Apache 2.0,Unknown,https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct +qwen2.5-72b-instruct,Qwen/Qwen2.5-72B-Instruct_bfloat16_a13fff9ad76700c7ecff2769f75943ba8395b4a7_True,Qwen/Qwen2.5-72B-Instruct,a13fff9ad76700c7ecff2769f75943ba8395b4a7,bfloat16,chatmodels,Original,Qwen2ForCausalLM,38.2120812616148,TRUE,IFEval,0.863837949972739,86.3837949972739,BBH,0.727274732174482,61.8732556687879,MATH Level 5,0.0120845921450151,1.20845921450151,GPQA,0.375,16.6666666666667,MUSR,0.420604166666667,11.7421875,MMLU-PRO,0.562583111702128,51.3981235224587,TRUE,FALSE,FALSE,FALSE,TRUE,2024-09-16,2024-10-16,1,Qwen/Qwen2.5-72B,other,594,72.706,33.0067683243991,25,31,Qwen2.5-72B-Instruct,1258,+3/-3,33591,Alibaba,Qwen,2024/9,https://qwenlm.github.io/blog/qwen2.5/ +qwen2.5-coder-32b-instruct,Qwen/Qwen2.5-Coder-32B-Instruct_float16_b47205940b83b5b484577359f71ee7b88472df67_False,Qwen/Qwen2.5-Coder-32B-Instruct,b47205940b83b5b484577359f71ee7b88472df67,float16,chatmodels,Original,Qwen2ForCausalLM,38.7525412608276,FALSE,IFEval,0.726526726862503,72.6526726862503,BBH,0.662522222240513,52.2665152094361,MATH Level 5,0.427492447129909,42.7492447129909,GPQA,0.348993288590604,13.1991051454139,MUSR,0.438583333333333,13.7229166666667,MMLU-PRO,0.441323138297872,37.924793144208,TRUE,FALSE,FALSE,FALSE,TRUE,2024-11-06,2024-12-10,1,Qwen/Qwen2.5-Coder-32B-Instruct (Merge),apache-2.0,1298,32,4.69438966297979,43,49,Qwen2.5-Coder-32B-Instruct,1217,+7/-8,5748,Alibaba,Apache 2.0,Unknown,https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct solar-10.7b-instruct-v1.0,upstage/SOLAR-10.7B-Instruct-v1.0_float16_c08c25ed66414a878fe0401a3596d536c083606c_True,upstage/SOLAR-10.7B-Instruct-v1.0,c08c25ed66414a878fe0401a3596d536c083606c,float16,chatmodels,Original,LlamaForCausalLM,19.6282553318946,TRUE,IFEval,0.473660997265035,47.3660997265035,BBH,0.516249494144699,31.8724018880021,MATH Level 5,0,0,GPQA,0.308724832214765,7.82997762863535,MUSR,0.3899375,6.9421875,MMLU-PRO,0.313829787234043,23.7588652482269,TRUE,FALSE,FALSE,FALSE,TRUE,2023-12-12,2024-06-12,1,upstage/SOLAR-10.7B-Instruct-v1.0 (Merge),cc-by-nc-4.0,617,10.732,0.782775785638588,125,125,SOLAR-10.7B-Instruct-v1.0,1062,+8/-9,4288,Upstage AI,CC-BY-NC-4.0,2023/11,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0 starling-lm-7b-alpha,berkeley-nest/Starling-LM-7B-alpha_bfloat16_1dddf3b95bc1391f6307299eb1c162c194bde9bd_True,berkeley-nest/Starling-LM-7B-alpha,1dddf3b95bc1391f6307299eb1c162c194bde9bd,bfloat16,chatmodels,Original,MistralForCausalLM,20.8267729304501,TRUE,IFEval,0.548049176185854,54.8049176185854,BBH,0.4440065261164,21.9540280871593,MATH Level 5,0.0830815709969789,8.30815709969789,GPQA,0.296979865771812,6.26398210290828,MUSR,0.412010416666667,9.50130208333333,MMLU-PRO,0.317154255319149,24.1282505910166,TRUE,FALSE,FALSE,FALSE,TRUE,2023-11-25,2024-06-12,0,berkeley-nest/Starling-LM-7B-alpha,apache-2.0,556,7.242,0.551628886692049,112,115,Starling-LM-7B-alpha,1089,+6/-5,10414,UC Berkeley,CC-BY-NC-4.0,2023/11,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha wizardlm-13b-v1.2,WizardLMTeam/WizardLM-13B-V1.2_float16_cf5f40382559f19e13874e45b39575171ca46ef8_False,WizardLMTeam/WizardLM-13B-V1.2,cf5f40382559f19e13874e45b39575171ca46ef8,float16,fine-tunedondomain-specificdatasets,Original,LlamaForCausalLM,15.164944624066,FALSE,IFEval,0.339246532533677,33.9246532533677,BBH,0.446199943646005,22.8886549780445,MATH Level 5,0.0181268882175227,1.81268882175227,GPQA,0.260906040268456,1.45413870246085,MUSR,0.43784375,14.03046875,MMLU-PRO,0.251911569148936,16.8790632387707,TRUE,FALSE,FALSE,FALSE,TRUE,2023-07-25,2024-06-12,0,WizardLMTeam/WizardLM-13B-V1.2,llama2,224,13,3.51945813008333,129,125,WizardLM-13b-v1.2,1059,+7/-7,7182,Microsoft,Llama 2 Community,2023/7,https://huggingface.co/WizardLM/WizardLM-13B-V1.2