diff --git a/csv/huggingface_v2.csv b/csv/huggingface_v2.csv index 1d3d0ea..0425cfc 100644 --- a/csv/huggingface_v2.csv +++ b/csv/huggingface_v2.csv @@ -1,49 +1,49 @@ t,model,average,ifeval,ifeval_raw,bbh,bbh_raw,math_lvl_5,math_lvl_5_raw,gpqa,gpqa_raw,musr,musr_raw,mmlupro,mmlupro_raw,type,architecture,weight_type,precision,not_merged,hub_license,params_b,hub_hearts,available_on_the_hub,model_sha,flagged,moe,submission_date,upload_to_hub_date,chat_template,maintainers_highlight,fullname,url -💬,Qwen/Qwen2-72B-Instruct,42.49,79.89,0.8,57.48,0.7,35.12,0.35,16.33,0.37,17.17,0.46,48.92,0.54,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2ForCausalLM,Original,bfloat16,TRUE,other,72,529,TRUE,1af63c698f59c4235668ec9c1395468cb7cd7e79,TRUE,TRUE,2024-06-26,2024-05-28,FALSE,TRUE,Qwen/Qwen2-72B-Instruct,https://huggingface.co/Qwen/Qwen2-72B-Instruct +💬,Qwen/Qwen2-72B-Instruct,42.49,79.89,0.8,57.48,0.7,35.12,0.35,16.33,0.37,17.17,0.46,48.92,0.54,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2ForCausalLM,Original,bfloat16,TRUE,other,72,530,TRUE,1af63c698f59c4235668ec9c1395468cb7cd7e79,TRUE,TRUE,2024-06-26,2024-05-28,FALSE,TRUE,Qwen/Qwen2-72B-Instruct,https://huggingface.co/Qwen/Qwen2-72B-Instruct 💬,meta-llama/Meta-Llama-3-70B-Instruct,36.18,80.99,0.81,50.19,0.65,23.34,0.23,4.92,0.29,10.92,0.42,46.74,0.52,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,llama3,70,1295,TRUE,7129260dd854a80eb10ace5f61c20324b472b31c,TRUE,TRUE,2024-06-12,2024-04-17,TRUE,TRUE,meta-llama/Meta-Llama-3-70B-Instruct,https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct -🟢,Qwen/Qwen2-72B,35.13,38.24,0.38,51.86,0.66,29.15,0.29,19.24,0.39,19.73,0.47,52.56,0.57,🟢 pretrained,Qwen2ForCausalLM,Original,bfloat16,TRUE,other,72,152,TRUE,87993795c78576318087f70b43fbf530eb7789e7,TRUE,TRUE,2024-06-26,2024-05-22,FALSE,TRUE,Qwen/Qwen2-72B,https://huggingface.co/Qwen/Qwen2-72B +🟢,Qwen/Qwen2-72B,35.13,38.24,0.38,51.86,0.66,29.15,0.29,19.24,0.39,19.73,0.47,52.56,0.57,🟢 pretrained,Qwen2ForCausalLM,Original,bfloat16,TRUE,other,72,153,TRUE,87993795c78576318087f70b43fbf530eb7789e7,TRUE,TRUE,2024-06-26,2024-05-22,FALSE,TRUE,Qwen/Qwen2-72B,https://huggingface.co/Qwen/Qwen2-72B 💬,mistralai/Mixtral-8x22B-Instruct-v0.1,33.89,71.84,0.72,44.11,0.61,18.73,0.19,16.44,0.37,13.49,0.43,38.7,0.45,"💬 chat models (RLHF, DPO, IFT, ...)",MixtralForCausalLM,Original,bfloat16,TRUE,apache-2.0,140,622,TRUE,b0c3516041d014f640267b14feb4e9a84c8e8c71,TRUE,FALSE,2024-06-12,2024-04-16,TRUE,TRUE,mistralai/Mixtral-8x22B-Instruct-v0.1,https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1 💬,HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1,33.77,65.11,0.65,47.5,0.63,18.35,0.18,17.11,0.38,14.72,0.45,39.85,0.46,"💬 chat models (RLHF, DPO, IFT, ...)",MixtralForCausalLM,Original,float16,TRUE,apache-2.0,140,253,TRUE,a3be084543d278e61b64cd600f28157afc79ffd3,TRUE,TRUE,2024-06-12,2024-04-10,TRUE,TRUE,HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1,https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 -💬,microsoft/Phi-3-medium-4k-instruct,32.67,64.23,0.64,49.38,0.64,16.99,0.17,11.52,0.34,13.05,0.43,40.84,0.47,"💬 chat models (RLHF, DPO, IFT, ...)",Phi3ForCausalLM,Original,bfloat16,TRUE,mit,13,171,TRUE,d194e4e74ffad5a5e193e26af25bcfc80c7f1ffc,TRUE,TRUE,2024-06-12,2024-05-07,TRUE,TRUE,microsoft/Phi-3-medium-4k-instruct,https://huggingface.co/microsoft/Phi-3-medium-4k-instruct +💬,microsoft/Phi-3-medium-4k-instruct,32.67,64.23,0.64,49.38,0.64,16.99,0.17,11.52,0.34,13.05,0.43,40.84,0.47,"💬 chat models (RLHF, DPO, IFT, ...)",Phi3ForCausalLM,Original,bfloat16,TRUE,mit,13,172,TRUE,d194e4e74ffad5a5e193e26af25bcfc80c7f1ffc,TRUE,TRUE,2024-06-12,2024-05-07,TRUE,TRUE,microsoft/Phi-3-medium-4k-instruct,https://huggingface.co/microsoft/Phi-3-medium-4k-instruct 💬,01-ai/Yi-1.5-34B-Chat,32.63,60.67,0.61,44.26,0.61,23.34,0.23,15.32,0.36,13.06,0.43,39.12,0.45,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,34,199,TRUE,f3128b2d02d82989daae566c0a7eadc621ca3254,TRUE,TRUE,2024-06-12,2024-05-10,TRUE,TRUE,01-ai/Yi-1.5-34B-Chat,https://huggingface.co/01-ai/Yi-1.5-34B-Chat -🔶,alpindale/WizardLM-2-8x22B,32.61,52.72,0.53,48.58,0.64,22.28,0.22,17.56,0.38,14.54,0.44,39.96,0.46,🔶 fine-tuned on domain-specific datasets,MixtralForCausalLM,Original,bfloat16,TRUE,apache-2.0,140,356,TRUE,087834da175523cffd66a7e19583725e798c1b4f,TRUE,TRUE,2024-06-28,2024-04-16,FALSE,FALSE,alpindale/WizardLM-2-8x22B,https://huggingface.co/alpindale/WizardLM-2-8x22B -💬,CohereForAI/c4ai-command-r-plus,30.86,76.64,0.77,39.92,0.58,7.55,0.08,7.38,0.31,20.42,0.48,33.24,0.4,"💬 chat models (RLHF, DPO, IFT, ...)",CohereForCausalLM,Original,float16,TRUE,cc-by-nc-4.0,103,1563,TRUE,fa1bd7fb1572ceb861bbbbecfa8af83b29fa8cca,TRUE,TRUE,2024-06-13,2024-04-03,TRUE,TRUE,CohereForAI/c4ai-command-r-plus,https://huggingface.co/CohereForAI/c4ai-command-r-plus -💬,internlm/internlm2_5-7b-chat,30.46,61.4,0.61,57.67,0.71,8.31,0.08,10.63,0.33,14.35,0.44,30.42,0.37,"💬 chat models (RLHF, DPO, IFT, ...)",InternLM2ForCausalLM,Original,float16,TRUE,other,7,88,TRUE,bebb00121ee105b823647c3ba2b1e152652edc33,TRUE,TRUE,2024-07-03,2024-06-27,TRUE,TRUE,internlm/internlm2_5-7b-chat,https://huggingface.co/internlm/internlm2_5-7b-chat +🔶,alpindale/WizardLM-2-8x22B,32.61,52.72,0.53,48.58,0.64,22.28,0.22,17.56,0.38,14.54,0.44,39.96,0.46,🔶 fine-tuned on domain-specific datasets,MixtralForCausalLM,Original,bfloat16,TRUE,apache-2.0,140,360,TRUE,087834da175523cffd66a7e19583725e798c1b4f,TRUE,TRUE,2024-06-28,2024-04-16,FALSE,FALSE,alpindale/WizardLM-2-8x22B,https://huggingface.co/alpindale/WizardLM-2-8x22B +💬,CohereForAI/c4ai-command-r-plus,30.86,76.64,0.77,39.92,0.58,7.55,0.08,7.38,0.31,20.42,0.48,33.24,0.4,"💬 chat models (RLHF, DPO, IFT, ...)",CohereForCausalLM,Original,float16,TRUE,cc-by-nc-4.0,103,1566,TRUE,fa1bd7fb1572ceb861bbbbecfa8af83b29fa8cca,TRUE,TRUE,2024-06-13,2024-04-03,TRUE,TRUE,CohereForAI/c4ai-command-r-plus,https://huggingface.co/CohereForAI/c4ai-command-r-plus +💬,internlm/internlm2_5-7b-chat,30.46,61.4,0.61,57.67,0.71,8.31,0.08,10.63,0.33,14.35,0.44,30.42,0.37,"💬 chat models (RLHF, DPO, IFT, ...)",InternLM2ForCausalLM,Original,float16,TRUE,other,7,89,TRUE,bebb00121ee105b823647c3ba2b1e152652edc33,TRUE,TRUE,2024-07-03,2024-06-27,TRUE,TRUE,internlm/internlm2_5-7b-chat,https://huggingface.co/internlm/internlm2_5-7b-chat 🟢,Qwen/Qwen1.5-110B,29.56,34.22,0.34,44.28,0.61,23.04,0.23,13.65,0.35,13.71,0.44,48.45,0.54,🟢 pretrained,Qwen2ForCausalLM,Original,bfloat16,TRUE,other,111,87,TRUE,16659038ecdcc771c1293cf47020fa7cc2750ee8,TRUE,TRUE,2024-06-13,2024-04-25,FALSE,TRUE,Qwen/Qwen1.5-110B,https://huggingface.co/Qwen/Qwen1.5-110B 🔶,abacusai/Smaug-72B-v0.1,29.56,51.7,0.52,42.42,0.59,17.75,0.18,9.62,0.32,15.39,0.45,40.46,0.46,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,other,72,460,TRUE,a1d657156f82c24b670158406378648233487011,TRUE,TRUE,2024-06-12,2024-02-02,FALSE,TRUE,abacusai/Smaug-72B-v0.1,https://huggingface.co/abacusai/Smaug-72B-v0.1 💬,Qwen/Qwen1.5-110B-Chat,29.22,59.39,0.59,44.98,0.62,0,0,12.19,0.34,16.29,0.45,42.5,0.48,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2ForCausalLM,Original,bfloat16,TRUE,other,111,117,TRUE,85f86cec25901f2dbd870a86e06756903c9a876a,TRUE,TRUE,2024-06-12,2024-04-25,TRUE,TRUE,Qwen/Qwen1.5-110B-Chat,https://huggingface.co/Qwen/Qwen1.5-110B-Chat -💬,microsoft/Phi-3-small-128k-instruct,28.75,63.44,0.63,45.57,0.62,0,0,9.84,0.32,14.7,0.44,38.94,0.45,"💬 chat models (RLHF, DPO, IFT, ...)",Phi3SmallForCausalLM,Original,bfloat16,TRUE,mit,7,140,TRUE,f80aaa30bfc64c2b8ab214b541d9050e97163bc4,TRUE,TRUE,2024-06-13,2024-05-07,TRUE,TRUE,microsoft/Phi-3-small-128k-instruct,https://huggingface.co/microsoft/Phi-3-small-128k-instruct +💬,microsoft/Phi-3-small-128k-instruct,28.75,63.44,0.63,45.57,0.62,0,0,9.84,0.32,14.7,0.44,38.94,0.45,"💬 chat models (RLHF, DPO, IFT, ...)",Phi3SmallForCausalLM,Original,bfloat16,TRUE,mit,7,142,TRUE,f80aaa30bfc64c2b8ab214b541d9050e97163bc4,TRUE,TRUE,2024-06-13,2024-05-07,TRUE,TRUE,microsoft/Phi-3-small-128k-instruct,https://huggingface.co/microsoft/Phi-3-small-128k-instruct 💬,01-ai/Yi-1.5-9B-Chat,27.71,60.46,0.6,36.95,0.56,11.63,0.12,11.3,0.33,12.84,0.43,33.06,0.4,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,8,111,TRUE,bc87d8557c98dc1e5fdef6ec23ed31088c4d3f35,TRUE,TRUE,2024-06-12,2024-05-10,TRUE,TRUE,01-ai/Yi-1.5-9B-Chat,https://huggingface.co/01-ai/Yi-1.5-9B-Chat 💬,Qwen/Qwen1.5-32B-Chat,27.1,55.32,0.55,44.55,0.61,6.65,0.07,7.49,0.31,10.2,0.42,38.41,0.45,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2ForCausalLM,Original,bfloat16,TRUE,other,32,102,TRUE,0997b012af6ddd5465d40465a8415535b2f06cfc,TRUE,TRUE,2024-06-12,2024-04-03,TRUE,TRUE,Qwen/Qwen1.5-32B-Chat,https://huggingface.co/Qwen/Qwen1.5-32B-Chat 💬,NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO,26.95,58.7,0.59,37.17,0.55,10.27,0.1,9.62,0.32,16.28,0.46,29.63,0.37,"💬 chat models (RLHF, DPO, IFT, ...)",MixtralForCausalLM,Original,bfloat16,TRUE,apache-2.0,46,393,TRUE,286ae6737d048ad1d965c2e830864df02db50f2f,TRUE,FALSE,2024-06-12,2024-01-11,TRUE,TRUE,NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO,https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO 💬,deepseek-ai/deepseek-llm-67b-chat,26.87,55.87,0.56,33.23,0.52,6.65,0.07,8.84,0.32,23.93,0.51,32.71,0.39,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,other,67,171,TRUE,79648bef7658bb824e4630740f6e1484c1b0620b,TRUE,TRUE,2024-06-12,2023-11-29,TRUE,TRUE,deepseek-ai/deepseek-llm-67b-chat,https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat 🔶,MaziyarPanahi/Llama-3-8B-Instruct-v0.8,26.75,75.12,0.75,28.27,0.5,7.1,0.07,7.38,0.31,10.92,0.42,31.68,0.39,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,other,8,3,TRUE,94d222b8447b600b9836da4036df9490b59fe966,TRUE,TRUE,2024-07-11,2024-05-01,TRUE,FALSE,MaziyarPanahi/Llama-3-8B-Instruct-v0.8,https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.8 🟢,Qwen/Qwen1.5-32B,26.69,32.97,0.33,38.98,0.57,26.66,0.27,10.63,0.33,12.04,0.43,38.89,0.45,🟢 pretrained,Qwen2ForCausalLM,Original,bfloat16,TRUE,other,32,77,TRUE,cefef80dc06a65f89d1d71d0adbc56d335ca2490,TRUE,TRUE,2024-06-13,2024-04-01,FALSE,TRUE,Qwen/Qwen1.5-32B,https://huggingface.co/Qwen/Qwen1.5-32B -🟢,01-ai/Yi-1.5-34B-32K,26.4,31.19,0.31,43.38,0.6,13.44,0.13,15.1,0.36,14.08,0.44,41.21,0.47,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,34,33,TRUE,2c03a29761e4174f20347a60fbe229be4383d48b,TRUE,TRUE,2024-06-12,2024-05-15,FALSE,TRUE,01-ai/Yi-1.5-34B-32K,https://huggingface.co/01-ai/Yi-1.5-34B-32K -🟢,meta-llama/Meta-Llama-3-70B,26.37,16.03,0.16,48.71,0.65,16.54,0.17,19.69,0.4,16.01,0.45,41.21,0.47,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,llama3,70,763,TRUE,b4d08b7db49d488da3ac49adf25a6b9ac01ae338,TRUE,TRUE,2024-06-12,2024-04-17,FALSE,TRUE,meta-llama/Meta-Llama-3-70B,https://huggingface.co/meta-llama/Meta-Llama-3-70B -💬,microsoft/Phi-3-mini-4k-instruct,25.97,56.13,0.56,39.27,0.57,11.63,0.12,9.28,0.32,7.64,0.4,31.85,0.39,"💬 chat models (RLHF, DPO, IFT, ...)",Phi3ForCausalLM,Original,bfloat16,TRUE,mit,3,852,TRUE,ff07dc01615f8113924aed013115ab2abd32115b,TRUE,TRUE,2024-06-12,2024-04-22,TRUE,TRUE,microsoft/Phi-3-mini-4k-instruct,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct +🟢,01-ai/Yi-1.5-34B-32K,26.4,31.19,0.31,43.38,0.6,13.44,0.13,15.1,0.36,14.08,0.44,41.21,0.47,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,34,34,TRUE,2c03a29761e4174f20347a60fbe229be4383d48b,TRUE,TRUE,2024-06-12,2024-05-15,FALSE,TRUE,01-ai/Yi-1.5-34B-32K,https://huggingface.co/01-ai/Yi-1.5-34B-32K +🟢,meta-llama/Meta-Llama-3-70B,26.37,16.03,0.16,48.71,0.65,16.54,0.17,19.69,0.4,16.01,0.45,41.21,0.47,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,llama3,70,764,TRUE,b4d08b7db49d488da3ac49adf25a6b9ac01ae338,TRUE,TRUE,2024-06-12,2024-04-17,FALSE,TRUE,meta-llama/Meta-Llama-3-70B,https://huggingface.co/meta-llama/Meta-Llama-3-70B +💬,microsoft/Phi-3-mini-4k-instruct,25.97,56.13,0.56,39.27,0.57,11.63,0.12,9.28,0.32,7.64,0.4,31.85,0.39,"💬 chat models (RLHF, DPO, IFT, ...)",Phi3ForCausalLM,Original,bfloat16,TRUE,mit,3,854,TRUE,ff07dc01615f8113924aed013115ab2abd32115b,TRUE,TRUE,2024-06-12,2024-04-22,TRUE,TRUE,microsoft/Phi-3-mini-4k-instruct,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct 🔶,Sao10K/L3-8B-Stheno-v3.2,25.76,68.73,0.69,32.02,0.52,8.53,0.09,8.05,0.31,6.45,0.38,30.76,0.38,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,cc-by-nc-4.0,8,169,TRUE,4bb828f6e1b1efd648c39b1ad682c44ff260f018,TRUE,TRUE,2024-06-30,2024-06-05,TRUE,FALSE,Sao10K/L3-8B-Stheno-v3.2,https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2 🟢,mistral-community/mixtral-8x22B-v0.3,25.55,25.83,0.26,45.73,0.63,16.84,0.17,17,0.38,7.46,0.4,40.44,0.46,🟢 pretrained,MixtralForCausalLM,Original,bfloat16,TRUE,apache-2.0,140,3,TRUE,211b177b79ab5ef245ee334d106c27623e786882,TRUE,FALSE,2024-06-13,2024-05-25,FALSE,TRUE,mistral-community/mixtral-8x22B-v0.3,https://huggingface.co/mistral-community/mixtral-8x22B-v0.3 🟢,mistralai/Mixtral-8x22B-v0.1,25.49,25.83,0.26,45.59,0.62,16.84,0.17,16.78,0.38,7.46,0.4,40.44,0.46,🟢 pretrained,MixtralForCausalLM,Original,bfloat16,TRUE,apache-2.0,140,168,TRUE,b03e260818710044a2f088d88fab12bb220884fb,TRUE,FALSE,2024-06-12,2024-04-16,FALSE,TRUE,mistralai/Mixtral-8x22B-v0.1,https://huggingface.co/mistralai/Mixtral-8x22B-v0.1 -💬,microsoft/Phi-3-mini-128k-instruct,25.49,59.76,0.6,37.1,0.56,8.91,0.09,9.06,0.32,7.71,0.39,30.38,0.37,"💬 chat models (RLHF, DPO, IFT, ...)",Phi3ForCausalLM,Original,bfloat16,TRUE,mit,3,1466,TRUE,5be6479b4bc06a081e8f4c6ece294241ccd32dec,TRUE,TRUE,2024-06-12,2024-04-22,TRUE,TRUE,microsoft/Phi-3-mini-128k-instruct,https://huggingface.co/microsoft/Phi-3-mini-128k-instruct +💬,microsoft/Phi-3-mini-128k-instruct,25.49,59.76,0.6,37.1,0.56,8.91,0.09,9.06,0.32,7.71,0.39,30.38,0.37,"💬 chat models (RLHF, DPO, IFT, ...)",Phi3ForCausalLM,Original,bfloat16,TRUE,mit,3,1467,TRUE,5be6479b4bc06a081e8f4c6ece294241ccd32dec,TRUE,TRUE,2024-06-12,2024-04-22,TRUE,TRUE,microsoft/Phi-3-mini-128k-instruct,https://huggingface.co/microsoft/Phi-3-mini-128k-instruct 🟢,01-ai/Yi-1.5-34B,25.43,28.41,0.28,42.75,0.6,14.05,0.14,15.44,0.37,11.22,0.42,40.73,0.47,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,34,43,TRUE,4b486f81c935a2dadde84c6baa1e1370d40a098f,TRUE,TRUE,2024-06-12,2024-05-11,FALSE,TRUE,01-ai/Yi-1.5-34B,https://huggingface.co/01-ai/Yi-1.5-34B 💬,CohereForAI/c4ai-command-r-v01,25.35,67.48,0.67,34.56,0.54,0,0,7.61,0.31,16.13,0.45,26.33,0.34,"💬 chat models (RLHF, DPO, IFT, ...)",CohereForCausalLM,Original,float16,TRUE,cc-by-nc-4.0,34,1032,TRUE,16881ccde1c68bbc7041280e6a66637bc46bfe88,TRUE,TRUE,2024-06-13,2024-03-11,TRUE,TRUE,CohereForAI/c4ai-command-r-v01,https://huggingface.co/CohereForAI/c4ai-command-r-v01 💬,databricks/dbrx-instruct,25.2,54.16,0.54,35.96,0.54,6.87,0.07,12.19,0.34,12.2,0.43,29.81,0.37,"💬 chat models (RLHF, DPO, IFT, ...)",DbrxForCausalLM,Original,bfloat16,TRUE,other,131,1089,TRUE,c0a9245908c187da8f43a81e538e67ff360904ea,TRUE,TRUE,2024-06-12,2024-03-26,TRUE,TRUE,databricks/dbrx-instruct,https://huggingface.co/databricks/dbrx-instruct 🟢,Qwen/Qwen2-57B-A14B,25.03,31.13,0.31,38.88,0.56,18.66,0.19,7.49,0.31,10.54,0.42,43.51,0.49,🟢 pretrained,Qwen2MoeForCausalLM,Original,bfloat16,TRUE,apache-2.0,57,41,TRUE,973e466c39ba76372a2ae464dbca0af3f5a5a2a9,TRUE,FALSE,2024-06-13,2024-05-22,FALSE,TRUE,Qwen/Qwen2-57B-A14B,https://huggingface.co/Qwen/Qwen2-57B-A14B -💬,Qwen/Qwen2-7B-Instruct,24.76,56.79,0.57,37.81,0.55,8.61,0.09,6.38,0.3,7.37,0.39,31.64,0.38,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2ForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,387,TRUE,41c66b0be1c3081f13defc6bdf946c2ef240d6a6,TRUE,TRUE,2024-06-12,2024-06-04,TRUE,TRUE,Qwen/Qwen2-7B-Instruct,https://huggingface.co/Qwen/Qwen2-7B-Instruct +💬,Qwen/Qwen2-7B-Instruct,24.76,56.79,0.57,37.81,0.55,8.61,0.09,6.38,0.3,7.37,0.39,31.64,0.38,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2ForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,389,TRUE,41c66b0be1c3081f13defc6bdf946c2ef240d6a6,TRUE,TRUE,2024-06-12,2024-06-04,TRUE,TRUE,Qwen/Qwen2-7B-Instruct,https://huggingface.co/Qwen/Qwen2-7B-Instruct 🔶,NousResearch/Hermes-2-Theta-Llama-3-8B,24.62,65.18,0.65,32.05,0.52,8.69,0.09,7.16,0.3,8.36,0.39,26.32,0.34,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,8,175,TRUE,885173e97ab8572b444f7db1290d5d0386e26816,TRUE,TRUE,2024-07-11,2024-05-05,TRUE,TRUE,NousResearch/Hermes-2-Theta-Llama-3-8B,https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B 💬,CohereForAI/aya-23-35B,24.62,64.62,0.65,34.86,0.54,2.64,0.03,5.93,0.29,13.47,0.43,26.18,0.34,"💬 chat models (RLHF, DPO, IFT, ...)",CohereForCausalLM,Original,float16,TRUE,cc-by-nc-4.0,34,219,TRUE,31d6fd858f20539a55401c7ad913086f54d9ca2c,TRUE,TRUE,2024-06-12,2024-05-19,TRUE,TRUE,CohereForAI/aya-23-35B,https://huggingface.co/CohereForAI/aya-23-35B 🔶,ZeusLabs/L3-Aethora-15B-V2,24.57,72.08,0.72,28.97,0.5,7.33,0.07,5.03,0.29,6.25,0.39,27.78,0.35,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,cc-by-sa-4.0,15,34,TRUE,2c601f116c37dd912c89357dbdbef879a637997e,TRUE,TRUE,2024-06-27,2024-06-27,TRUE,FALSE,ZeusLabs/L3-Aethora-15B-V2,https://huggingface.co/ZeusLabs/L3-Aethora-15B-V2 -💬,mistralai/Mixtral-8x7B-Instruct-v0.1,24.35,53.95,0.54,34.02,0.53,9.06,0.09,7.61,0.31,12.11,0.43,29.36,0.36,"💬 chat models (RLHF, DPO, IFT, ...)",MixtralForCausalLM,Original,bfloat16,TRUE,apache-2.0,46,3972,TRUE,1e637f2d7cb0a9d6fb1922f305cb784995190a83,TRUE,FALSE,2024-06-12,2023-12-10,TRUE,TRUE,mistralai/Mixtral-8x7B-Instruct-v0.1,https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1 +💬,mistralai/Mixtral-8x7B-Instruct-v0.1,24.35,53.95,0.54,34.02,0.53,9.06,0.09,7.61,0.31,12.11,0.43,29.36,0.36,"💬 chat models (RLHF, DPO, IFT, ...)",MixtralForCausalLM,Original,bfloat16,TRUE,apache-2.0,46,3976,TRUE,1e637f2d7cb0a9d6fb1922f305cb784995190a83,TRUE,FALSE,2024-06-12,2023-12-10,TRUE,TRUE,mistralai/Mixtral-8x7B-Instruct-v0.1,https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1 💬,argilla/notux-8x7b-v1,24.13,54.53,0.55,32.86,0.52,8.69,0.09,7.49,0.31,11.57,0.42,29.66,0.37,"💬 chat models (RLHF, DPO, IFT, ...)",MixtralForCausalLM,Original,bfloat16,TRUE,apache-2.0,46,163,TRUE,0b29f9afcbae2ab4c5085638d8f5a7f6d44c6b17,TRUE,FALSE,2024-06-12,2023-12-12,TRUE,TRUE,argilla/notux-8x7b-v1,https://huggingface.co/argilla/notux-8x7b-v1 💬,vicgalle/Roleplay-Llama-3-8B,23.94,73.2,0.73,28.55,0.5,8.69,0.09,1.45,0.26,1.68,0.35,30.09,0.37,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,float16,TRUE,apache-2.0,8,29,TRUE,57297eb57dcc2c116f061d9dda341094203da01b,TRUE,TRUE,2024-06-26,2024-04-19,TRUE,FALSE,vicgalle/Roleplay-Llama-3-8B,https://huggingface.co/vicgalle/Roleplay-Llama-3-8B -💬,meta-llama/Meta-Llama-3-8B-Instruct,23.91,74.08,0.74,28.24,0.5,8.69,0.09,1.23,0.26,1.6,0.36,29.6,0.37,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,llama3,8,3061,TRUE,e1945c40cd546c78e41f1151f4db032b271faeaa,TRUE,TRUE,2024-06-12,2024-04-17,TRUE,TRUE,meta-llama/Meta-Llama-3-8B-Instruct,https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct -💬,01-ai/Yi-34B-Chat,23.9,46.99,0.47,37.62,0.56,4.31,0.04,11.74,0.34,8.36,0.4,34.37,0.41,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,34,337,TRUE,2e528b6a80fb064a0a746c5ca43114b135e30464,TRUE,TRUE,2024-06-12,2023-11-22,TRUE,TRUE,01-ai/Yi-34B-Chat,https://huggingface.co/01-ai/Yi-34B-Chat +💬,meta-llama/Meta-Llama-3-8B-Instruct,23.91,74.08,0.74,28.24,0.5,8.69,0.09,1.23,0.26,1.6,0.36,29.6,0.37,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,llama3,8,3074,TRUE,e1945c40cd546c78e41f1151f4db032b271faeaa,TRUE,TRUE,2024-06-12,2024-04-17,TRUE,TRUE,meta-llama/Meta-Llama-3-8B-Instruct,https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct +💬,01-ai/Yi-34B-Chat,23.9,46.99,0.47,37.62,0.56,4.31,0.04,11.74,0.34,8.36,0.4,34.37,0.41,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,34,338,TRUE,2e528b6a80fb064a0a746c5ca43114b135e30464,TRUE,TRUE,2024-06-12,2023-11-22,TRUE,TRUE,01-ai/Yi-34B-Chat,https://huggingface.co/01-ai/Yi-34B-Chat 💬,abacusai/Smaug-34B-v0.1,23.76,50.16,0.5,34.26,0.54,0,0,10.63,0.33,8.13,0.4,39.37,0.45,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,34,58,TRUE,34d54c65a0247d5eb694973106c816d9c0ad3fc2,TRUE,TRUE,2024-06-12,2024-01-25,TRUE,TRUE,abacusai/Smaug-34B-v0.1,https://huggingface.co/abacusai/Smaug-34B-v0.1 🟢,Qwen/Qwen2-7B,23.66,31.49,0.31,34.71,0.53,18.81,0.19,7.27,0.3,14.32,0.44,35.37,0.42,🟢 pretrained,Qwen2ForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,91,TRUE,453ed1575b739b5b03ce3758b23befdb0967f40e,TRUE,TRUE,2024-06-09,2024-06-04,FALSE,TRUE,Qwen/Qwen2-7B,https://huggingface.co/Qwen/Qwen2-7B 💬,NousResearch/Nous-Hermes-2-SOLAR-10.7B,23.32,52.79,0.53,34.99,0.54,5.21,0.05,5.82,0.29,13.83,0.44,27.31,0.35,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,10,200,TRUE,14c1fbe2f71acdcd58247b30d5439bd572d52386,TRUE,TRUE,2024-06-12,2024-01-01,TRUE,TRUE,NousResearch/Nous-Hermes-2-SOLAR-10.7B,https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B 🔶,UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3,23.31,68.28,0.68,29.74,0.51,7.33,0.07,2.01,0.27,3.09,0.37,29.38,0.36,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,8,63,TRUE,f73dafc2923acd56f115f21f76e9d14f8d19a63e,TRUE,TRUE,2024-07-02,2024-06-25,TRUE,FALSE,UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3,https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 -💬,google/gemma-2-9b-it,23.18,76.95,0.77,38.55,0.57,0,0,12.42,0.34,9.38,0.4,1.78,0.12,"💬 chat models (RLHF, DPO, IFT, ...)",Gemma2ForCausalLM,Original,bfloat16,TRUE,gemma,9,254,TRUE,1937c70277fcc5f7fb0fc772fc5bc69378996e71,TRUE,TRUE,2024-07-11,2024-06-24,TRUE,TRUE,google/gemma-2-9b-it,https://huggingface.co/google/gemma-2-9b-it +💬,google/gemma-2-9b-it,23.18,76.95,0.77,38.55,0.57,0,0,12.42,0.34,9.38,0.4,1.78,0.12,"💬 chat models (RLHF, DPO, IFT, ...)",Gemma2ForCausalLM,Original,bfloat16,TRUE,gemma,9,257,TRUE,1937c70277fcc5f7fb0fc772fc5bc69378996e71,TRUE,TRUE,2024-07-11,2024-06-24,TRUE,TRUE,google/gemma-2-9b-it,https://huggingface.co/google/gemma-2-9b-it 💬,UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3,23.06,67.03,0.67,29.72,0.51,7.18,0.07,2.01,0.27,2.89,0.36,29.53,0.37,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,float16,TRUE,apache-2.0,8,63,TRUE,f73dafc2923acd56f115f21f76e9d14f8d19a63e,TRUE,TRUE,2024-06-28,2024-06-25,TRUE,FALSE,UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3,https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 💬,MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3,23.02,49.26,0.49,37.66,0.55,2.95,0.03,9.06,0.32,7.75,0.4,31.42,0.38,"💬 chat models (RLHF, DPO, IFT, ...)",Phi3ForCausalLM,Original,bfloat16,TRUE,mit,3,9,TRUE,e1f70c3724c728aadd1c7c1bb279487494f7059e,TRUE,TRUE,2024-06-26,2024-05-10,TRUE,FALSE,MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3,https://huggingface.co/MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3 💬,LLM360/K2-Chat,22.93,51.52,0.52,33.79,0.54,1.59,0.02,7.49,0.31,16.82,0.46,26.34,0.34,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,65,29,TRUE,5454f2d28031c9127e4227c873ca2f154e02e4c7,TRUE,TRUE,2024-06-12,2024-05-22,TRUE,TRUE,LLM360/K2-Chat,https://huggingface.co/LLM360/K2-Chat @@ -54,7 +54,7 @@ t,model,average,ifeval,ifeval_raw,bbh,bbh_raw,math_lvl_5,math_lvl_5_raw,gpqa,gpq 💬,openchat/openchat-3.5-1210,22.56,60.37,0.6,23.24,0.45,6.87,0.07,6.82,0.3,14.28,0.44,23.81,0.31,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,274,TRUE,801f5459b7577241500785f11c2b026912badd6e,TRUE,TRUE,2024-06-12,2023-12-12,TRUE,TRUE,openchat/openchat-3.5-1210,https://huggingface.co/openchat/openchat-3.5-1210 🔶,WizardLMTeam/WizardLM-70B-V1.0,22.32,49.51,0.5,37.54,0.56,3.47,0.03,2.13,0.27,14.09,0.44,27.18,0.34,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,float16,TRUE,llama2,70,230,TRUE,54aaecaff7d0790eb9f0ecea1cc267a94cc66949,TRUE,TRUE,2024-06-12,2023-08-09,FALSE,TRUE,WizardLMTeam/WizardLM-70B-V1.0,https://huggingface.co/WizardLMTeam/WizardLM-70B-V1.0 🟢,01-ai/Yi-34B,22.26,30.46,0.3,35.54,0.55,4.46,0.04,15.55,0.37,9.65,0.41,37.91,0.44,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,34,1266,TRUE,e1e7da8c75cfd5c44522228599fd4d2990cedd1c,TRUE,TRUE,2024-06-12,2023-11-01,FALSE,TRUE,01-ai/Yi-34B,https://huggingface.co/01-ai/Yi-34B -💬,01-ai/Yi-1.5-6B-Chat,22.05,48.02,0.48,23.55,0.46,12.54,0.13,9.06,0.32,14.7,0.44,24.41,0.32,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,6,30,TRUE,3f64d3f159c6ad8494227bb77e2a7baef8cd808b,TRUE,TRUE,2024-06-12,2024-05-11,TRUE,TRUE,01-ai/Yi-1.5-6B-Chat,https://huggingface.co/01-ai/Yi-1.5-6B-Chat +💬,01-ai/Yi-1.5-6B-Chat,22.05,48.02,0.48,23.55,0.46,12.54,0.13,9.06,0.32,14.7,0.44,24.41,0.32,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,6,31,TRUE,3f64d3f159c6ad8494227bb77e2a7baef8cd808b,TRUE,TRUE,2024-06-12,2024-05-11,TRUE,TRUE,01-ai/Yi-1.5-6B-Chat,https://huggingface.co/01-ai/Yi-1.5-6B-Chat 🤝,mlabonne/NeuralDaredevil-8B-abliterated,22.04,45.6,0.46,30.33,0.51,8.01,0.08,7.61,0.31,9.08,0.4,31.65,0.38,🤝 base merges and moerges,LlamaForCausalLM,Original,float16,TRUE,other,8,107,TRUE,2f4a5e8a8522f19dff345c7189b7891468763061,TRUE,TRUE,2024-07-03,2024-05-27,TRUE,TRUE,mlabonne/NeuralDaredevil-8B-abliterated,https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated 🟢,01-ai/Yi-1.5-9B,21.95,29.36,0.29,30.5,0.51,10.2,0.1,17.23,0.38,12.03,0.43,32.4,0.39,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,8,42,TRUE,8cfde9604384c50137bee480b8cef8a08e5ae81d,TRUE,TRUE,2024-06-12,2024-05-11,FALSE,TRUE,01-ai/Yi-1.5-9B,https://huggingface.co/01-ai/Yi-1.5-9B 💬,NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT,21.78,57.31,0.57,30.59,0.51,1.74,0.02,6.94,0.3,11.14,0.42,22.96,0.31,"💬 chat models (RLHF, DPO, IFT, ...)",MixtralForCausalLM,Original,bfloat16,TRUE,apache-2.0,46,55,TRUE,4c06af2684730f75a6874b95e8bf6058105d9612,TRUE,FALSE,2024-06-12,2023-12-26,TRUE,TRUE,NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT,https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT @@ -65,18 +65,18 @@ t,model,average,ifeval,ifeval_raw,bbh,bbh_raw,math_lvl_5,math_lvl_5_raw,gpqa,gpq 💬,teknium/OpenHermes-2-Mistral-7B,21.33,52.86,0.53,29.25,0.49,3.85,0.04,4.47,0.28,16.06,0.45,21.46,0.29,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,256,TRUE,4c6e34123b140ce773a8433cae5410949289102c,TRUE,TRUE,2024-06-12,2023-10-12,TRUE,TRUE,teknium/OpenHermes-2-Mistral-7B,https://huggingface.co/teknium/OpenHermes-2-Mistral-7B 💬,teknium/OpenHermes-2.5-Mistral-7B,21.22,55.71,0.56,27.77,0.49,4.46,0.04,4.47,0.28,12.06,0.42,22.83,0.31,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,792,TRUE,24c0bea14d53e6f67f1fbe2eca5bfe7cae389b33,TRUE,TRUE,2024-06-12,2023-10-29,TRUE,TRUE,teknium/OpenHermes-2.5-Mistral-7B,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B 💬,Qwen/Qwen1.5-14B-Chat,21.02,47.68,0.48,32.76,0.52,0,0,2.68,0.27,13.93,0.44,29.09,0.36,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2ForCausalLM,Original,bfloat16,TRUE,other,14,103,TRUE,9492b22871f43e975435455f5c616c77fe7a50ec,TRUE,TRUE,2024-06-12,2024-01-30,TRUE,TRUE,Qwen/Qwen1.5-14B-Chat,https://huggingface.co/Qwen/Qwen1.5-14B-Chat -💬,NousResearch/Nous-Hermes-2-Mistral-7B-DPO,21.01,57.63,0.58,27.79,0.49,4.23,0.04,5.7,0.29,8.33,0.4,22.39,0.3,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,157,TRUE,ebec0a691037d38955727d6949798429a63929dd,TRUE,TRUE,2024-06-12,2024-02-18,TRUE,TRUE,NousResearch/Nous-Hermes-2-Mistral-7B-DPO,https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO +💬,NousResearch/Nous-Hermes-2-Mistral-7B-DPO,21.01,57.63,0.58,27.79,0.49,4.23,0.04,5.7,0.29,8.33,0.4,22.39,0.3,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,158,TRUE,ebec0a691037d38955727d6949798429a63929dd,TRUE,TRUE,2024-06-12,2024-02-18,TRUE,TRUE,NousResearch/Nous-Hermes-2-Mistral-7B-DPO,https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO 🔶,Intel/neural-chat-7b-v3-1,21,46.87,0.47,29.74,0.51,3.17,0.03,5.37,0.29,22.24,0.5,18.64,0.27,🔶 fine-tuned on domain-specific datasets,MistralForCausalLM,Original,float16,TRUE,apache-2.0,7,545,TRUE,c0d379a49c1c0579529d5e6f2e936ddb759552a8,TRUE,TRUE,2024-06-12,2023-11-14,FALSE,TRUE,Intel/neural-chat-7b-v3-1,https://huggingface.co/Intel/neural-chat-7b-v3-1 💬,berkeley-nest/Starling-LM-7B-alpha,20.64,54.8,0.55,21.95,0.44,7.18,0.07,6.26,0.3,9.5,0.41,24.13,0.32,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,552,TRUE,1dddf3b95bc1391f6307299eb1c162c194bde9bd,TRUE,TRUE,2024-06-12,2023-11-25,TRUE,TRUE,berkeley-nest/Starling-LM-7B-alpha,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha 🟢,Qwen/Qwen1.5-14B,20.22,29.05,0.29,30.06,0.51,16.47,0.16,5.93,0.29,10.46,0.42,29.37,0.36,🟢 pretrained,Qwen2ForCausalLM,Original,bfloat16,TRUE,other,14,36,TRUE,dce4b190d34470818e5bec2a92cb8233aaa02ca2,TRUE,TRUE,2024-06-13,2024-01-22,FALSE,TRUE,Qwen/Qwen1.5-14B,https://huggingface.co/Qwen/Qwen1.5-14B 🔶,Intel/neural-chat-7b-v3-3,19.99,47.63,0.48,27.75,0.49,0.68,0.01,5.26,0.29,20.58,0.49,18.05,0.26,🔶 fine-tuned on domain-specific datasets,MistralForCausalLM,Original,float16,TRUE,apache-2.0,7,73,TRUE,bdd31cf498d13782cc7497cba5896996ce429f91,TRUE,TRUE,2024-06-12,2023-12-09,FALSE,TRUE,Intel/neural-chat-7b-v3-3,https://huggingface.co/Intel/neural-chat-7b-v3-3 🟢,01-ai/Yi-34B-200K,19.8,15.42,0.15,36.02,0.54,4.46,0.04,14.21,0.36,9.41,0.38,39.27,0.45,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,34,313,TRUE,8ac1a1ebe011df28b78ccd08012aeb2222443c77,TRUE,TRUE,2024-06-12,2023-11-06,FALSE,TRUE,01-ai/Yi-34B-200K,https://huggingface.co/01-ai/Yi-34B-200K -💬,upstage/SOLAR-10.7B-Instruct-v1.0,19.63,47.37,0.47,31.87,0.52,0,0,7.83,0.31,6.94,0.39,23.76,0.31,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,float16,TRUE,cc-by-nc-4.0,10,599,TRUE,c08c25ed66414a878fe0401a3596d536c083606c,TRUE,TRUE,2024-06-12,2023-12-12,TRUE,TRUE,upstage/SOLAR-10.7B-Instruct-v1.0,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0 +💬,upstage/SOLAR-10.7B-Instruct-v1.0,19.63,47.37,0.47,31.87,0.52,0,0,7.83,0.31,6.94,0.39,23.76,0.31,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,float16,TRUE,cc-by-nc-4.0,10,600,TRUE,c08c25ed66414a878fe0401a3596d536c083606c,TRUE,TRUE,2024-06-12,2023-12-12,TRUE,TRUE,upstage/SOLAR-10.7B-Instruct-v1.0,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0 🔶,RLHFlow/LLaMA3-iterative-DPO-final,19.63,53.34,0.53,29.79,0.51,0,0,4.47,0.28,5.08,0.37,25.08,0.33,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,llama3,8,37,TRUE,40b73bd07a019795837f80579fe95470484ca82b,TRUE,TRUE,2024-06-26,2024-05-17,TRUE,FALSE,RLHFlow/LLaMA3-iterative-DPO-final,https://huggingface.co/RLHFlow/LLaMA3-iterative-DPO-final 🟢,01-ai/Yi-1.5-9B-32K,19.61,23.03,0.23,28.94,0.5,9.59,0.1,14.54,0.36,10.83,0.42,30.72,0.38,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,8,18,TRUE,116561dfae63af90f9d163b43077629e0e916bb1,TRUE,TRUE,2024-06-12,2024-05-15,FALSE,TRUE,01-ai/Yi-1.5-9B-32K,https://huggingface.co/01-ai/Yi-1.5-9B-32K 🤝,mlabonne/Beyonder-4x7B-v3,19.31,56.08,0.56,24.56,0.47,4.76,0.05,4.7,0.29,8.93,0.4,16.81,0.25,🤝 base merges and moerges,MixtralForCausalLM,Original,float16,FALSE,cc-by-nc-4.0,24,56,TRUE,8e923fa480f511ab54d79b44b0487768bdd3de4e,TRUE,FALSE,2024-06-12,2024-03-21,TRUE,TRUE,mlabonne/Beyonder-4x7B-v3,https://huggingface.co/mlabonne/Beyonder-4x7B-v3 🟢,mistralai/Mixtral-8x7B-v0.1,19.23,23.5,0.24,29.73,0.5,8.84,0.09,9.28,0.32,12.55,0.43,31.5,0.38,🟢 pretrained,MixtralForCausalLM,Original,bfloat16,TRUE,apache-2.0,46,1591,TRUE,985aa055896a8f943d4a9f2572e6ea1341823841,TRUE,FALSE,2024-06-12,2023-12-01,FALSE,TRUE,mistralai/Mixtral-8x7B-v0.1,https://huggingface.co/mistralai/Mixtral-8x7B-v0.1 -💬,mistralai/Mistral-7B-Instruct-v0.3,19.11,54.65,0.55,25.57,0.47,3.17,0.03,3.91,0.28,4.3,0.37,23.06,0.31,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,791,TRUE,83e9aa141f2e28c82232fea5325f54edf17c43de,TRUE,TRUE,2024-06-12,2024-05-22,TRUE,TRUE,mistralai/Mistral-7B-Instruct-v0.3,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3 +💬,mistralai/Mistral-7B-Instruct-v0.3,19.11,54.65,0.55,25.57,0.47,3.17,0.03,3.91,0.28,4.3,0.37,23.06,0.31,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,793,TRUE,83e9aa141f2e28c82232fea5325f54edf17c43de,TRUE,TRUE,2024-06-12,2024-05-22,TRUE,TRUE,mistralai/Mistral-7B-Instruct-v0.3,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3 💬,HuggingFaceH4/zephyr-7b-alpha,18.52,51.91,0.52,23.89,0.46,1.51,0.02,6.38,0.3,7.5,0.39,19.94,0.28,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,mit,7,1085,TRUE,2ce2d025864af849b3e5029e2ec9d568eeda892d,TRUE,TRUE,2024-06-12,2023-10-09,TRUE,TRUE,HuggingFaceH4/zephyr-7b-alpha,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha 💬,mistralai/Mistral-7B-Instruct-v0.2,18.44,54.96,0.55,22.91,0.45,2.64,0.03,3.47,0.28,7.61,0.4,19.08,0.27,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,2417,TRUE,41b61a33a2483885c981aa79e0df6b32407ed873,TRUE,TRUE,2024-06-12,2023-12-11,TRUE,TRUE,mistralai/Mistral-7B-Instruct-v0.2,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2 💬,cognitivecomputations/dolphin-2.9-llama3-8b,18.3,38.5,0.39,27.86,0.49,5.06,0.05,4.92,0.29,13.79,0.44,19.68,0.28,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,other,8,370,TRUE,5aeb036f9215c558b483a654a8c6e1cc22e841bf,TRUE,TRUE,2024-06-12,2024-04-20,TRUE,TRUE,cognitivecomputations/dolphin-2.9-llama3-8b,https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b @@ -85,7 +85,7 @@ t,model,average,ifeval,ifeval_raw,bbh,bbh_raw,math_lvl_5,math_lvl_5_raw,gpqa,gpq 💬,gradientai/Llama-3-8B-Instruct-Gradient-1048k,18.12,44.56,0.45,21.01,0.43,4.38,0.04,3.69,0.28,13.52,0.43,21.56,0.29,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,llama3,8,649,TRUE,8697fb25cb77c852311e03b4464b8467471d56a4,TRUE,TRUE,2024-06-12,2024-04-29,TRUE,TRUE,gradientai/Llama-3-8B-Instruct-Gradient-1048k,https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-1048k 🟢,THUDM/glm-4-9b,18.01,14.26,0.14,35.81,0.55,0,0,8.84,0.32,14.19,0.44,34.94,0.41,🟢 pretrained,ChatGLMModelM,Original,bfloat16,TRUE,other,9,82,TRUE,99a140996f9d4f197842fb6b1aab217a42e27ef3,TRUE,TRUE,2024-07-04,2024-06-04,FALSE,FALSE,THUDM/glm-4-9b,https://huggingface.co/THUDM/glm-4-9b 🔶,Intel/neural-chat-7b-v3,17.94,27.78,0.28,30.21,0.5,2.19,0.02,5.59,0.29,23.02,0.51,18.87,0.27,🔶 fine-tuned on domain-specific datasets,MistralForCausalLM,Original,float16,TRUE,apache-2.0,7,65,TRUE,fc679274dfcd28a8b6087634f71af7ed2a0659c4,TRUE,TRUE,2024-06-12,2023-10-25,FALSE,TRUE,Intel/neural-chat-7b-v3,https://huggingface.co/Intel/neural-chat-7b-v3 -💬,HuggingFaceH4/zephyr-7b-beta,17.72,49.5,0.5,21.49,0.43,2.42,0.02,5.37,0.29,7.73,0.39,19.79,0.28,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,mit,7,1519,TRUE,b70e0c9a2d9e14bd1e812d3c398e5f313e93b473,TRUE,TRUE,2024-06-12,2023-10-26,TRUE,TRUE,HuggingFaceH4/zephyr-7b-beta,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta +💬,HuggingFaceH4/zephyr-7b-beta,17.72,49.5,0.5,21.49,0.43,2.42,0.02,5.37,0.29,7.73,0.39,19.79,0.28,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,mit,7,1521,TRUE,b70e0c9a2d9e14bd1e812d3c398e5f313e93b473,TRUE,TRUE,2024-06-12,2023-10-26,TRUE,TRUE,HuggingFaceH4/zephyr-7b-beta,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta 💬,Open-Orca/Mistral-7B-OpenOrca,17.62,49.78,0.5,25.84,0.48,2.95,0.03,2.91,0.27,5.89,0.39,18.37,0.27,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,663,TRUE,4a37328cef00f524d3791b1c0cc559a3cc6af14d,TRUE,TRUE,2024-06-12,2023-09-29,TRUE,TRUE,Open-Orca/Mistral-7B-OpenOrca,https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca 🟢,01-ai/Yi-9B,17.61,27.09,0.27,27.63,0.49,4.38,0.04,9.06,0.32,8.91,0.41,28.6,0.36,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,8,181,TRUE,b4a466d95091696285409f1dcca3028543cb39da,TRUE,TRUE,2024-06-12,2024-03-01,FALSE,TRUE,01-ai/Yi-9B,https://huggingface.co/01-ai/Yi-9B 💬,mlabonne/AlphaMonarch-7B,17.59,49.39,0.49,23.95,0.46,3.85,0.04,2.68,0.27,9.32,0.41,16.36,0.25,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,float16,FALSE,cc-by-nc-4.0,7,146,TRUE,3de065d84411d74e5b3590f67f52b0b71faf6161,TRUE,TRUE,2024-06-12,2024-02-14,TRUE,TRUE,mlabonne/AlphaMonarch-7B,https://huggingface.co/mlabonne/AlphaMonarch-7B @@ -113,55 +113,55 @@ t,model,average,ifeval,ifeval_raw,bbh,bbh_raw,math_lvl_5,math_lvl_5_raw,gpqa,gpq 💬,mlabonne/OrpoLlama-3-8B,14.87,36.53,0.37,21.95,0.44,3.85,0.04,3.91,0.28,4.01,0.36,18.95,0.27,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,float16,TRUE,other,8,52,TRUE,7f200e4c84ad0daa3ff6bc414012d8d0bacbf90e,TRUE,TRUE,2024-06-12,2024-04-18,TRUE,TRUE,mlabonne/OrpoLlama-3-8B,https://huggingface.co/mlabonne/OrpoLlama-3-8B 💬,Qwen/Qwen1.5-MoE-A2.7B-Chat,14.82,37.95,0.38,20.04,0.43,0,0,3.24,0.27,6.33,0.39,21.37,0.29,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2MoeForCausalLM,Original,bfloat16,TRUE,other,14,108,TRUE,ec052fda178e241c7c443468d2fa1db6618996be,TRUE,FALSE,2024-06-12,2024-03-14,TRUE,TRUE,Qwen/Qwen1.5-MoE-A2.7B-Chat,https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B-Chat 💬,deepseek-ai/deepseek-llm-7b-chat,14.77,41.71,0.42,11.26,0.36,1.74,0.02,2.13,0.27,19.21,0.47,12.59,0.21,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,other,7,73,TRUE,afbda8b347ec881666061fa67447046fc5164ec8,TRUE,TRUE,2024-06-12,2023-11-29,TRUE,TRUE,deepseek-ai/deepseek-llm-7b-chat,https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat -🟢,mistralai/Mistral-7B-v0.1,14.5,23.86,0.24,22.02,0.44,2.49,0.02,5.59,0.29,10.68,0.41,22.36,0.3,🟢 pretrained,MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,3295,TRUE,26bca36bde8333b5d7f72e9ed20ccda6a618af24,TRUE,TRUE,2024-06-12,2023-09-20,FALSE,TRUE,mistralai/Mistral-7B-v0.1,https://huggingface.co/mistralai/Mistral-7B-v0.1 +🟢,mistralai/Mistral-7B-v0.1,14.5,23.86,0.24,22.02,0.44,2.49,0.02,5.59,0.29,10.68,0.41,22.36,0.3,🟢 pretrained,MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,3296,TRUE,26bca36bde8333b5d7f72e9ed20ccda6a618af24,TRUE,TRUE,2024-06-12,2023-09-20,FALSE,TRUE,mistralai/Mistral-7B-v0.1,https://huggingface.co/mistralai/Mistral-7B-v0.1 🔶,teknium/CollectiveCognition-v1.1-Mistral-7B,14.23,27.9,0.28,23.48,0.45,2.95,0.03,4.92,0.29,5.73,0.39,20.41,0.28,🔶 fine-tuned on domain-specific datasets,MistralForCausalLM,Original,float16,TRUE,apache-2.0,7,78,TRUE,5f57f70ec99450c70da2540e94dd7fd67be4b23c,TRUE,TRUE,2024-06-12,2023-10-04,FALSE,TRUE,teknium/CollectiveCognition-v1.1-Mistral-7B,https://huggingface.co/teknium/CollectiveCognition-v1.1-Mistral-7B 🔶,TencentARC/Mistral_Pro_8B_v0.1,14.2,21.15,0.21,22.89,0.45,5.66,0.06,4.03,0.28,11.83,0.42,19.61,0.28,🔶 fine-tuned on domain-specific datasets,MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,8,64,TRUE,366f159fc5b314ba2a955209d2bca4600f84dac0,TRUE,TRUE,2024-06-12,2024-02-22,FALSE,TRUE,TencentARC/Mistral_Pro_8B_v0.1,https://huggingface.co/TencentARC/Mistral_Pro_8B_v0.1 🟢,mistralai/Mistral-7B-v0.3,14.17,22.66,0.23,24.04,0.45,2.64,0.03,5.59,0.29,8.36,0.4,21.7,0.3,🟢 pretrained,MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,300,TRUE,b67d6a03ca097c5122fa65904fce0413500bf8c8,TRUE,TRUE,2024-06-12,2024-05-22,FALSE,TRUE,mistralai/Mistral-7B-v0.3,https://huggingface.co/mistralai/Mistral-7B-v0.3 🔶,microsoft/Orca-2-7b,14.15,21.99,0.22,22.57,0.45,0.83,0.01,0.78,0.26,24.09,0.5,14.65,0.23,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,other,7,208,TRUE,60e31e6bdcf582ad103b807cb74b73ee1d2c4b17,TRUE,TRUE,2024-06-12,2023-11-14,FALSE,TRUE,microsoft/Orca-2-7b,https://huggingface.co/microsoft/Orca-2-7b 🟢,mistral-community/Mistral-7B-v0.2,14.15,22.66,0.23,23.95,0.45,2.64,0.03,5.59,0.29,8.36,0.4,21.7,0.3,🟢 pretrained,MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,226,TRUE,2c3e624962b1a3f3fbf52e15969565caa7bc064a,TRUE,TRUE,2024-06-12,2024-03-23,FALSE,TRUE,mistral-community/Mistral-7B-v0.2,https://huggingface.co/mistral-community/Mistral-7B-v0.2 💬,01-ai/Yi-6B-Chat,14,33.95,0.34,17,0.41,0.68,0.01,5.93,0.29,3.57,0.37,22.9,0.31,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,6,62,TRUE,01f7fabb6cfb26efeb764da4a0a19cad2c754232,TRUE,TRUE,2024-06-12,2023-11-22,TRUE,TRUE,01-ai/Yi-6B-Chat,https://huggingface.co/01-ai/Yi-6B-Chat -💬,Qwen/Qwen2-1.5B-Instruct,13.92,33.71,0.34,13.7,0.39,5.82,0.06,1.57,0.26,12.03,0.43,16.68,0.25,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2ForCausalLM,Original,bfloat16,TRUE,apache-2.0,1,60,TRUE,ba1cf1846d7df0a0591d6c00649f57e798519da8,TRUE,TRUE,2024-06-12,2024-06-03,TRUE,TRUE,Qwen/Qwen2-1.5B-Instruct,https://huggingface.co/Qwen/Qwen2-1.5B-Instruct +💬,Qwen/Qwen2-1.5B-Instruct,13.92,33.71,0.34,13.7,0.39,5.82,0.06,1.57,0.26,12.03,0.43,16.68,0.25,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2ForCausalLM,Original,bfloat16,TRUE,apache-2.0,1,61,TRUE,ba1cf1846d7df0a0591d6c00649f57e798519da8,TRUE,TRUE,2024-06-12,2024-06-03,TRUE,TRUE,Qwen/Qwen2-1.5B-Instruct,https://huggingface.co/Qwen/Qwen2-1.5B-Instruct 🟢,stabilityai/stablelm-2-12b,13.86,15.69,0.16,22.69,0.45,3.47,0.03,3.8,0.28,14.49,0.45,23.02,0.31,🟢 pretrained,StableLmForCausalLM,Original,bfloat16,TRUE,other,12,108,TRUE,fead13ddbf4492970666650c3cd6f85f485411ec,TRUE,TRUE,2024-06-12,2024-03-21,FALSE,TRUE,stabilityai/stablelm-2-12b,https://huggingface.co/stabilityai/stablelm-2-12b 🔶,openchat/openchat_v3.2,13.81,29.81,0.3,20.32,0.43,1.13,0.01,2.68,0.27,13.1,0.43,15.8,0.24,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,llama2,13,42,TRUE,acc7ce92558681e749678648189812f15c1465fe,TRUE,TRUE,2024-06-12,2023-07-30,FALSE,TRUE,openchat/openchat_v3.2,https://huggingface.co/openchat/openchat_v3.2 🟢,tiiuae/falcon-11B,13.78,32.61,0.33,21.94,0.44,2.34,0.02,2.8,0.27,7.53,0.4,15.44,0.24,🟢 pretrained,FalconForCausalLM,Original,bfloat16,TRUE,unknown,11,190,TRUE,066e3bf4e2d9aaeefa129af0a6d39727d27816b3,TRUE,TRUE,2024-06-09,2024-05-09,FALSE,TRUE,tiiuae/falcon-11B,https://huggingface.co/tiiuae/falcon-11B 🟢,01-ai/Yi-6B,13.6,28.93,0.29,19.41,0.43,1.51,0.02,2.57,0.27,7.04,0.39,22.12,0.3,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,6,366,TRUE,7f7fb7662fd8ec09029364f408053c954986c8e5,TRUE,TRUE,2024-06-12,2023-11-01,FALSE,TRUE,01-ai/Yi-6B,https://huggingface.co/01-ai/Yi-6B 💬,mistralai/Mistral-7B-Instruct-v0.1,13.57,45.02,0.45,13.79,0.38,1.51,0.02,0,0.24,5.77,0.38,15.34,0.24,"💬 chat models (RLHF, DPO, IFT, ...)",MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,1470,TRUE,73068f3702d050a2fd5aa2ca1e612e5036429398,TRUE,TRUE,2024-06-27,2023-09-27,TRUE,TRUE,mistralai/Mistral-7B-Instruct-v0.1,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1 🟢,NousResearch/Yarn-Mistral-7b-64k,13.43,20.8,0.21,20.23,0.43,3.02,0.03,5.37,0.29,9.88,0.41,21.27,0.29,🟢 pretrained,MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,49,TRUE,0273c624561fcecc8e8f4030492a9307aa60f945,TRUE,TRUE,2024-06-12,2023-10-31,FALSE,TRUE,NousResearch/Yarn-Mistral-7b-64k,https://huggingface.co/NousResearch/Yarn-Mistral-7b-64k -🟢,meta-llama/Meta-Llama-3-8B,13.41,14.55,0.15,24.5,0.46,3.25,0.03,7.38,0.31,6.24,0.36,24.55,0.32,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,llama3,8,5244,TRUE,62bd457b6fe961a42a631306577e622c83876cb6,TRUE,TRUE,2024-06-12,2024-04-17,FALSE,TRUE,meta-llama/Meta-Llama-3-8B,https://huggingface.co/meta-llama/Meta-Llama-3-8B +🟢,meta-llama/Meta-Llama-3-8B,13.41,14.55,0.15,24.5,0.46,3.25,0.03,7.38,0.31,6.24,0.36,24.55,0.32,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,llama3,8,5256,TRUE,62bd457b6fe961a42a631306577e622c83876cb6,TRUE,TRUE,2024-06-12,2024-04-17,FALSE,TRUE,meta-llama/Meta-Llama-3-8B,https://huggingface.co/meta-llama/Meta-Llama-3-8B 🟢,google/recurrentgemma-9b,13.26,30.76,0.31,14.8,0.39,4.83,0.05,4.7,0.29,6.6,0.38,17.88,0.26,🟢 pretrained,RecurrentGemmaForCausalLM,Original,bfloat16,TRUE,gemma,9,56,TRUE,7b0ed98fb889ba8bdfa7c690f08f2e57a7c48dae,TRUE,TRUE,2024-07-04,2024-06-07,FALSE,TRUE,google/recurrentgemma-9b,https://huggingface.co/google/recurrentgemma-9b 🟢,NousResearch/Yarn-Mistral-7b-128k,13.16,19.34,0.19,20.63,0.43,2.49,0.02,6.49,0.3,8.95,0.41,21.03,0.29,🟢 pretrained,MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,566,TRUE,d09f1f8ed437d61c1aff94c1beabee554843dcdd,TRUE,TRUE,2024-06-12,2023-10-31,FALSE,TRUE,NousResearch/Yarn-Mistral-7b-128k,https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k 💬,google/gemma-7b-it,12.84,38.68,0.39,11.94,0.36,1.59,0.02,4.59,0.28,12.53,0.43,7.72,0.17,"💬 chat models (RLHF, DPO, IFT, ...)",GemmaForCausalLM,Original,bfloat16,TRUE,gemma,8,1105,TRUE,18329f019fb74ca4b24f97371785268543d687d2,TRUE,TRUE,2024-06-12,2024-02-13,TRUE,TRUE,google/gemma-7b-it,https://huggingface.co/google/gemma-7b-it 🔶,openchat/openchat_v3.2_super,12.84,28.62,0.29,19.15,0.42,1.59,0.02,1.9,0.26,9.92,0.42,15.84,0.24,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,llama2,13,36,TRUE,9479cc37d43234a57a33628637d1aca0293d745a,TRUE,TRUE,2024-06-12,2023-09-04,FALSE,TRUE,openchat/openchat_v3.2_super,https://huggingface.co/openchat/openchat_v3.2_super 💬,meta-llama/Llama-2-70b-chat-hf,12.73,49.58,0.5,4.61,0.3,0.91,0.01,1.9,0.26,3.48,0.37,15.92,0.24,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,float16,TRUE,llama2,68,2120,TRUE,e9149a12809580e8602995856f8098ce973d1080,TRUE,TRUE,2024-06-12,2023-07-14,TRUE,TRUE,meta-llama/Llama-2-70b-chat-hf,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf -🔶,Sao10K/L3-8B-Stheno-v3.3-32K,12.57,46.04,0.46,13.51,0.38,0.98,0.01,0.89,0.26,4.07,0.37,9.95,0.19,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,cc-by-nc-4.0,8,36,TRUE,1a59d163e079c7e7f1542553d085853119960f0c,TRUE,TRUE,2024-06-26,2024-06-22,TRUE,FALSE,Sao10K/L3-8B-Stheno-v3.3-32K,https://huggingface.co/Sao10K/L3-8B-Stheno-v3.3-32K +🔶,Sao10K/L3-8B-Stheno-v3.3-32K,12.57,46.04,0.46,13.51,0.38,0.98,0.01,0.89,0.26,4.07,0.37,9.95,0.19,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,cc-by-nc-4.0,8,37,TRUE,1a59d163e079c7e7f1542553d085853119960f0c,TRUE,TRUE,2024-06-26,2024-06-22,TRUE,FALSE,Sao10K/L3-8B-Stheno-v3.3-32K,https://huggingface.co/Sao10K/L3-8B-Stheno-v3.3-32K 🟢,Qwen/Qwen1.5-MoE-A2.7B,12.42,26.6,0.27,18.84,0.41,0.15,0,1.23,0.26,7.97,0.4,19.75,0.28,🟢 pretrained,Qwen2MoeForCausalLM,Original,bfloat16,TRUE,other,14,181,TRUE,1a758c50ecb6350748b9ce0a99d2352fd9fc11c9,TRUE,FALSE,2024-06-13,2024-02-29,FALSE,TRUE,Qwen/Qwen1.5-MoE-A2.7B,https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B 💬,stabilityai/stablelm-zephyr-3b,12.33,36.83,0.37,14.76,0.39,4.08,0.04,0,0.24,9.79,0.42,8.53,0.18,"💬 chat models (RLHF, DPO, IFT, ...)",StableLmForCausalLM,Original,bfloat16,TRUE,other,2,236,TRUE,a14f62d95754d96aea2be6e24c0f6966636797b9,TRUE,TRUE,2024-06-12,2023-11-21,TRUE,TRUE,stabilityai/stablelm-zephyr-3b,https://huggingface.co/stabilityai/stablelm-zephyr-3b 💬,Qwen/Qwen1.5-4B-Chat,12.33,31.57,0.32,16.3,0.4,0.98,0.01,2.24,0.27,7.36,0.4,15.51,0.24,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2ForCausalLM,Original,bfloat16,TRUE,other,3,34,TRUE,a7a4d4945d28bac955554c9abd2f74a71ebbf22f,TRUE,TRUE,2024-06-12,2024-01-30,TRUE,TRUE,Qwen/Qwen1.5-4B-Chat,https://huggingface.co/Qwen/Qwen1.5-4B-Chat -🟢,bigcode/starcoder2-15b,12.21,27.35,0.27,20.24,0.44,4.83,0.05,2.91,0.27,2.93,0.35,15.03,0.24,🟢 pretrained,Starcoder2ForCausalLM,Original,bfloat16,TRUE,bigcode-openrail-m,15,533,TRUE,46d44742909c03ac8cee08eb03fdebce02e193ec,TRUE,TRUE,2024-06-09,2024-02-20,FALSE,TRUE,bigcode/starcoder2-15b,https://huggingface.co/bigcode/starcoder2-15b +🟢,bigcode/starcoder2-15b,12.21,27.35,0.27,20.24,0.44,4.83,0.05,2.91,0.27,2.93,0.35,15.03,0.24,🟢 pretrained,Starcoder2ForCausalLM,Original,bfloat16,TRUE,bigcode-openrail-m,15,534,TRUE,46d44742909c03ac8cee08eb03fdebce02e193ec,TRUE,TRUE,2024-06-09,2024-02-20,FALSE,TRUE,bigcode/starcoder2-15b,https://huggingface.co/bigcode/starcoder2-15b 🔶,teknium/OpenHermes-13B,12.12,26.68,0.27,18.21,0.42,0.83,0.01,3.02,0.27,8.53,0.4,15.44,0.24,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,mit,13,53,TRUE,bcad6fff9f8591e091d2d57356a3f102197e8c5f,TRUE,TRUE,2024-06-12,2023-09-06,FALSE,TRUE,teknium/OpenHermes-13B,https://huggingface.co/teknium/OpenHermes-13B 🔶,TencentARC/MetaMath-Mistral-Pro,12.01,21.19,0.21,22.37,0.44,4.61,0.05,2.57,0.27,4.99,0.35,16.35,0.25,🔶 fine-tuned on domain-specific datasets,MistralForCausalLM,Original,bfloat16,TRUE,apache-2.0,8,5,TRUE,3835d38de15ed2a04c32aca879b782fc50e390bf,TRUE,TRUE,2024-06-12,2024-02-26,FALSE,TRUE,TencentARC/MetaMath-Mistral-Pro,https://huggingface.co/TencentARC/MetaMath-Mistral-Pro 🟢,01-ai/Yi-6B-200K,11.9,8.43,0.08,20.15,0.43,1.21,0.01,4.25,0.28,16.84,0.46,20.49,0.28,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,apache-2.0,6,174,TRUE,4a74338e778a599f313e9fa8f5bc08c717604420,TRUE,TRUE,2024-06-12,2023-11-06,FALSE,TRUE,01-ai/Yi-6B-200K,https://huggingface.co/01-ai/Yi-6B-200K 🔶,Replete-AI/Replete-Coder-Llama3-8B,11.66,47.29,0.47,7.06,0.33,2.95,0.03,1.45,0.26,7.51,0.4,3.67,0.13,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,other,8,32,TRUE,2aca75c53e7eb2f523889ab1a279e349b8f1b0e8,TRUE,TRUE,2024-06-26,2024-06-24,TRUE,FALSE,Replete-AI/Replete-Coder-Llama3-8B,https://huggingface.co/Replete-AI/Replete-Coder-Llama3-8B -🟢,tiiuae/falcon-40b,11.33,24.96,0.25,16.58,0.4,1.36,0.01,3.13,0.27,5.19,0.36,16.72,0.25,🟢 pretrained,FalconForCausalLM,Original,bfloat16,TRUE,apache-2.0,40,2417,TRUE,4a70170c215b36a3cce4b4253f6d0612bb7d4146,TRUE,TRUE,2024-06-09,2023-05-24,FALSE,TRUE,tiiuae/falcon-40b,https://huggingface.co/tiiuae/falcon-40b +🟢,tiiuae/falcon-40b,11.33,24.96,0.25,16.58,0.4,1.36,0.01,3.13,0.27,5.19,0.36,16.72,0.25,🟢 pretrained,FalconForCausalLM,Original,bfloat16,TRUE,apache-2.0,40,2416,TRUE,4a70170c215b36a3cce4b4253f6d0612bb7d4146,TRUE,TRUE,2024-06-09,2023-05-24,FALSE,TRUE,tiiuae/falcon-40b,https://huggingface.co/tiiuae/falcon-40b 🟢,Qwen/Qwen1.5-4B,11.29,24.45,0.24,16.25,0.41,2.42,0.02,3.58,0.28,4.82,0.36,16.22,0.25,🟢 pretrained,Qwen2ForCausalLM,Original,bfloat16,TRUE,other,3,34,TRUE,a66363a0c24e2155c561e4b53c658b1d3965474e,TRUE,TRUE,2024-06-13,2024-01-22,FALSE,TRUE,Qwen/Qwen1.5-4B,https://huggingface.co/Qwen/Qwen1.5-4B 🔶,Replete-AI/Replete-Coder-Qwen2-1.5b,11.07,30.14,0.3,10.43,0.35,0.91,0.01,2.46,0.27,9.74,0.41,12.74,0.21,🔶 fine-tuned on domain-specific datasets,Qwen2ForCausalLM,Original,bfloat16,TRUE,apache-2.0,1,21,TRUE,86fcccbf921b7eb8a4d348e4a3cde0beb63d6626,TRUE,TRUE,2024-06-26,2024-06-23,TRUE,FALSE,Replete-AI/Replete-Coder-Qwen2-1.5b,https://huggingface.co/Replete-AI/Replete-Coder-Qwen2-1.5b 💬,meta-llama/Llama-2-13b-chat-hf,11,39.85,0.4,7.16,0.33,0.6,0.01,0,0.23,8.16,0.4,10.26,0.19,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,float16,TRUE,llama2,13,995,TRUE,a2cb7a712bb6e5e736ca7f8cd98167f81a0b5bd8,TRUE,TRUE,2024-06-12,2023-07-13,TRUE,TRUE,meta-llama/Llama-2-13b-chat-hf,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf 🟢,meta-llama/Llama-2-13b-hf,10.99,24.82,0.25,17.22,0.41,1.06,0.01,4.14,0.28,3.39,0.35,15.31,0.24,🟢 pretrained,LlamaForCausalLM,Original,float16,TRUE,llama2,13,561,TRUE,5c31dfb671ce7cfe2d7bb7c04375e44c55e815b1,TRUE,TRUE,2024-06-12,2023-07-13,FALSE,TRUE,meta-llama/Llama-2-13b-hf,https://huggingface.co/meta-llama/Llama-2-13b-hf -💬,THUDM/glm-4-9b-chat,10.97,0,0,25.21,0.47,0,0,8.5,0.31,8.06,0.4,24.07,0.32,"💬 chat models (RLHF, DPO, IFT, ...)",ChatGLMModelM,Original,bfloat16,TRUE,other,9,459,TRUE,04419001bc63e05e70991ade6da1f91c4aeec278,TRUE,TRUE,2024-07-09,2024-06-04,TRUE,FALSE,THUDM/glm-4-9b-chat,https://huggingface.co/THUDM/glm-4-9b-chat -🔶,lmsys/vicuna-7b-v1.5,10.78,23.52,0.24,15.15,0.39,0.76,0.01,1.12,0.26,11.42,0.42,12.74,0.21,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,float16,TRUE,llama2,7,263,TRUE,3321f76e3f527bd14065daf69dad9344000a201d,TRUE,TRUE,2024-06-12,2023-07-29,FALSE,TRUE,lmsys/vicuna-7b-v1.5,https://huggingface.co/lmsys/vicuna-7b-v1.5 +💬,THUDM/glm-4-9b-chat,10.97,0,0,25.21,0.47,0,0,8.5,0.31,8.06,0.4,24.07,0.32,"💬 chat models (RLHF, DPO, IFT, ...)",ChatGLMModelM,Original,bfloat16,TRUE,other,9,462,TRUE,04419001bc63e05e70991ade6da1f91c4aeec278,TRUE,TRUE,2024-07-09,2024-06-04,TRUE,FALSE,THUDM/glm-4-9b-chat,https://huggingface.co/THUDM/glm-4-9b-chat +🔶,lmsys/vicuna-7b-v1.5,10.78,23.52,0.24,15.15,0.39,0.76,0.01,1.12,0.26,11.42,0.42,12.74,0.21,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,float16,TRUE,llama2,7,265,TRUE,3321f76e3f527bd14065daf69dad9344000a201d,TRUE,TRUE,2024-06-12,2023-07-29,FALSE,TRUE,lmsys/vicuna-7b-v1.5,https://huggingface.co/lmsys/vicuna-7b-v1.5 💬,allenai/OLMo-7B-Instruct-hf,10.73,34.73,0.35,13.16,0.37,0.68,0.01,2.8,0.27,4.33,0.38,8.69,0.18,"💬 chat models (RLHF, DPO, IFT, ...)",OlmoForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,0,TRUE,2ea947518df93433aa71219f29b36c72ac63be95,TRUE,TRUE,2024-06-27,2024-06-04,TRUE,TRUE,allenai/OLMo-7B-Instruct-hf,https://huggingface.co/allenai/OLMo-7B-Instruct-hf 💬,internlm/internlm2-chat-1_8b,10.5,23.87,0.24,20.67,0.45,2.42,0.02,2.13,0.27,4.61,0.36,9.33,0.18,"💬 chat models (RLHF, DPO, IFT, ...)",InternLM2ForCausalLM,Original,bfloat16,TRUE,other,1,24,TRUE,4e226eeb354499f4d34ef4c27f6939f377475cc1,TRUE,TRUE,2024-06-12,2024-01-30,TRUE,TRUE,internlm/internlm2-chat-1_8b,https://huggingface.co/internlm/internlm2-chat-1_8b 💬,tiiuae/falcon-40b-instruct,10.41,24.54,0.25,17.22,0.41,1.51,0.02,0,0.25,5.16,0.38,14.02,0.23,"💬 chat models (RLHF, DPO, IFT, ...)",FalconForCausalLM,Original,bfloat16,TRUE,apache-2.0,40,1170,TRUE,ecb78d97ac356d098e79f0db222c9ce7c5d9ee5f,TRUE,TRUE,2024-06-09,2023-05-25,FALSE,TRUE,tiiuae/falcon-40b-instruct,https://huggingface.co/tiiuae/falcon-40b-instruct -🟢,Qwen/Qwen2-1.5B,10.32,21.13,0.21,11.78,0.36,6.27,0.06,1.9,0.26,3.59,0.37,17.24,0.26,🟢 pretrained,Qwen2ForCausalLM,Original,bfloat16,TRUE,apache-2.0,1,43,TRUE,8a16abf2848eda07cc5253dec660bf1ce007ad7a,TRUE,TRUE,2024-06-09,2024-05-31,FALSE,TRUE,Qwen/Qwen2-1.5B,https://huggingface.co/Qwen/Qwen2-1.5B +🟢,Qwen/Qwen2-1.5B,10.32,21.13,0.21,11.78,0.36,6.27,0.06,1.9,0.26,3.59,0.37,17.24,0.26,🟢 pretrained,Qwen2ForCausalLM,Original,bfloat16,TRUE,apache-2.0,1,44,TRUE,8a16abf2848eda07cc5253dec660bf1ce007ad7a,TRUE,TRUE,2024-06-09,2024-05-31,FALSE,TRUE,Qwen/Qwen2-1.5B,https://huggingface.co/Qwen/Qwen2-1.5B 💬,deepseek-ai/deepseek-moe-16b-chat,10.14,36.63,0.37,6.57,0.33,1.66,0.02,0,0.22,5.26,0.38,10.71,0.2,"💬 chat models (RLHF, DPO, IFT, ...)",DeepseekForCausalLM,Original,bfloat16,TRUE,other,16,110,TRUE,eefd8ac7e8dc90e095129fe1a537d5e236b2e57c,TRUE,FALSE,2024-06-12,2024-01-09,TRUE,TRUE,deepseek-ai/deepseek-moe-16b-chat,https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat 🔶,teknium/OpenHermes-7B,9.48,18.13,0.18,12.08,0.36,1.06,0.01,2.57,0.27,12.68,0.43,10.37,0.19,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,float16,TRUE,mit,7,13,TRUE,9f55d6eb15f1edd52ee1fd863a220aa682e78a00,TRUE,TRUE,2024-06-12,2023-09-14,FALSE,TRUE,teknium/OpenHermes-7B,https://huggingface.co/teknium/OpenHermes-7B -💬,meta-llama/Llama-2-7b-chat-hf,9.4,39.65,0.4,4.49,0.31,0.68,0.01,0.56,0.25,3.48,0.37,7.52,0.17,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,float16,TRUE,llama2,6,3687,TRUE,f5db02db724555f92da89c216ac04704f23d4590,TRUE,TRUE,2024-06-12,2023-07-13,TRUE,TRUE,meta-llama/Llama-2-7b-chat-hf,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf +💬,meta-llama/Llama-2-7b-chat-hf,9.4,39.65,0.4,4.49,0.31,0.68,0.01,0.56,0.25,3.48,0.37,7.52,0.17,"💬 chat models (RLHF, DPO, IFT, ...)",LlamaForCausalLM,Original,float16,TRUE,llama2,6,3688,TRUE,f5db02db724555f92da89c216ac04704f23d4590,TRUE,TRUE,2024-06-12,2023-07-13,TRUE,TRUE,meta-llama/Llama-2-7b-chat-hf,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf 🔶,NousResearch/Nous-Hermes-llama-2-7b,9.28,17.29,0.17,13.79,0.38,0.68,0.01,1.79,0.26,11.68,0.43,10.44,0.19,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,mit,6,67,TRUE,b7c3ec54b754175e006ef75696a2ba3802697078,TRUE,TRUE,2024-06-12,2023-07-25,FALSE,TRUE,NousResearch/Nous-Hermes-llama-2-7b,https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b 💬,stabilityai/stablelm-2-zephyr-1_6b,9.26,32.79,0.33,6.71,0.34,2.11,0.02,0,0.24,5.99,0.35,7.93,0.17,"💬 chat models (RLHF, DPO, IFT, ...)",StableLmForCausalLM,Original,float16,TRUE,other,1,174,TRUE,2f275b1127d59fc31e4f7c7426d528768ada9ea4,TRUE,TRUE,2024-06-12,2024-01-19,TRUE,TRUE,stabilityai/stablelm-2-zephyr-1_6b,https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b 🟢,Qwen/Qwen1.5-1.8B,9.12,21.54,0.22,9.76,0.35,2.27,0.02,7.38,0.31,3.96,0.36,9.8,0.19,🟢 pretrained,Qwen2ForCausalLM,Original,bfloat16,TRUE,other,1,42,TRUE,7846de7ed421727b318d6605a0bfab659da2c067,TRUE,TRUE,2024-06-13,2024-01-22,FALSE,TRUE,Qwen/Qwen1.5-1.8B,https://huggingface.co/Qwen/Qwen1.5-1.8B 💬,Qwen/Qwen1.5-1.8B-Chat,9.01,20.19,0.2,5.91,0.33,0.45,0,6.38,0.3,12.18,0.43,8.93,0.18,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2ForCausalLM,Original,bfloat16,TRUE,other,1,42,TRUE,e482ee3f73c375a627a16fdf66fd0c8279743ca6,TRUE,TRUE,2024-06-12,2024-01-30,TRUE,TRUE,Qwen/Qwen1.5-1.8B-Chat,https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat 🔶,TencentARC/LLaMA-Pro-8B,8.78,22.77,0.23,9.29,0.35,1.66,0.02,1.34,0.26,8.59,0.4,9.01,0.18,🔶 fine-tuned on domain-specific datasets,LlamaForCausalLM,Original,bfloat16,TRUE,llama2,8,169,TRUE,7115e7179060e0623d1ee9ff4476faed7e478d8c,TRUE,TRUE,2024-06-12,2024-01-05,FALSE,TRUE,TencentARC/LLaMA-Pro-8B,https://huggingface.co/TencentARC/LLaMA-Pro-8B -🟢,meta-llama/Llama-2-7b-hf,8.72,25.19,0.25,10.35,0.35,1.21,0.01,2.24,0.27,3.76,0.37,9.57,0.19,🟢 pretrained,LlamaForCausalLM,Original,float16,TRUE,llama2,6,1569,TRUE,01c7f73d771dfac7d292323805ebc428287df4f9,TRUE,TRUE,2024-06-12,2023-07-13,FALSE,TRUE,meta-llama/Llama-2-7b-hf,https://huggingface.co/meta-llama/Llama-2-7b-hf +🟢,meta-llama/Llama-2-7b-hf,8.72,25.19,0.25,10.35,0.35,1.21,0.01,2.24,0.27,3.76,0.37,9.57,0.19,🟢 pretrained,LlamaForCausalLM,Original,float16,TRUE,llama2,6,1570,TRUE,01c7f73d771dfac7d292323805ebc428287df4f9,TRUE,TRUE,2024-06-12,2023-07-13,FALSE,TRUE,meta-llama/Llama-2-7b-hf,https://huggingface.co/meta-llama/Llama-2-7b-hf 💬,stabilityai/stablelm-2-1_6b-chat,8.63,30.6,0.31,7.49,0.34,1.06,0.01,0,0.25,5.71,0.36,6.91,0.16,"💬 chat models (RLHF, DPO, IFT, ...)",StableLmForCausalLM,Original,bfloat16,TRUE,other,1,26,TRUE,f3fe67057c2789ae1bb1fe42b038da99840d4f13,TRUE,TRUE,2024-06-12,2024-04-08,TRUE,TRUE,stabilityai/stablelm-2-1_6b-chat,https://huggingface.co/stabilityai/stablelm-2-1_6b-chat 🟢,internlm/internlm2-1_8b,8.58,21.98,0.22,13.63,0.39,1.13,0.01,0,0.25,8.23,0.38,6.54,0.16,🟢 pretrained,InternLM2ForCausalLM,Original,bfloat16,TRUE,other,8,24,TRUE,c24f301c7374ad9f9b58d1ea80f68b5f57cbca13,TRUE,TRUE,2024-06-12,2024-01-30,FALSE,TRUE,internlm/internlm2-1_8b,https://huggingface.co/internlm/internlm2-1_8b 🟢,NousResearch/Yarn-Llama-2-13b-128k,8.39,16.55,0.17,13.51,0.38,1.13,0.01,1.12,0.26,3.39,0.35,14.67,0.23,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,,13,113,TRUE,4e3e87a067f64f8814c83dd5e3bad92dcf8a2391,TRUE,TRUE,2024-06-13,2023-08-30,FALSE,TRUE,NousResearch/Yarn-Llama-2-13b-128k,https://huggingface.co/NousResearch/Yarn-Llama-2-13b-128k @@ -175,10 +175,10 @@ t,model,average,ifeval,ifeval_raw,bbh,bbh_raw,math_lvl_5,math_lvl_5_raw,gpqa,gpq 🟢,deepseek-ai/deepseek-moe-16b-base,7.37,24.5,0.24,8.36,0.34,1.81,0.02,0.56,0.25,3.36,0.37,5.61,0.15,🟢 pretrained,DeepseekForCausalLM,Original,bfloat16,TRUE,other,16,76,TRUE,521d2bc4fb69a3f3ae565310fcc3b65f97af2580,TRUE,FALSE,2024-06-12,2024-01-08,FALSE,TRUE,deepseek-ai/deepseek-moe-16b-base,https://huggingface.co/deepseek-ai/deepseek-moe-16b-base 🟢,google/gemma-2b,7.27,20.38,0.2,8.25,0.34,2.72,0.03,0.67,0.26,7.56,0.4,4.06,0.14,🟢 pretrained,GemmaForCausalLM,Original,bfloat16,TRUE,gemma,2,797,TRUE,2ac59a5d7bf4e1425010f0d457dde7d146658953,TRUE,TRUE,2024-06-12,2024-02-08,FALSE,TRUE,google/gemma-2b,https://huggingface.co/google/gemma-2b 🟢,stabilityai/stablelm-3b-4e1t,7.26,22.03,0.22,9.01,0.35,0.68,0.01,0,0.24,4.42,0.38,7.43,0.17,🟢 pretrained,StableLmForCausalLM,Original,bfloat16,TRUE,cc-by-sa-4.0,2,305,TRUE,fa4a6a92fca83c3b4223a3c9bf792887090ebfba,TRUE,TRUE,2024-06-12,2023-09-29,FALSE,TRUE,stabilityai/stablelm-3b-4e1t,https://huggingface.co/stabilityai/stablelm-3b-4e1t -💬,google/gemma-2b-it,7.22,26.9,0.27,5.21,0.32,0.45,0,3.8,0.28,3.03,0.33,3.92,0.14,"💬 chat models (RLHF, DPO, IFT, ...)",GemmaForCausalLM,Original,bfloat16,TRUE,gemma,2,582,TRUE,de144fb2268dee1066f515465df532c05e699d48,TRUE,TRUE,2024-06-12,2024-02-08,TRUE,TRUE,google/gemma-2b-it,https://huggingface.co/google/gemma-2b-it +💬,google/gemma-2b-it,7.22,26.9,0.27,5.21,0.32,0.45,0,3.8,0.28,3.03,0.33,3.92,0.14,"💬 chat models (RLHF, DPO, IFT, ...)",GemmaForCausalLM,Original,bfloat16,TRUE,gemma,2,583,TRUE,de144fb2268dee1066f515465df532c05e699d48,TRUE,TRUE,2024-06-12,2024-02-08,TRUE,TRUE,google/gemma-2b-it,https://huggingface.co/google/gemma-2b-it 🟢,NousResearch/Yarn-Llama-2-7b-64k,7.12,17,0.17,7.04,0.33,0.98,0.01,1.9,0.26,6.93,0.39,8.87,0.18,🟢 pretrained,LlamaForCausalLM,Original,bfloat16,TRUE,,7,23,TRUE,08491431ac3b50add7443f5d4c02850801d877be,TRUE,TRUE,2024-06-13,2023-08-30,FALSE,TRUE,NousResearch/Yarn-Llama-2-7b-64k,https://huggingface.co/NousResearch/Yarn-Llama-2-7b-64k 🟢,Qwen/Qwen2-0.5B,7.06,18.67,0.19,7.99,0.33,2.57,0.03,0.78,0.26,4.6,0.38,7.76,0.17,🟢 pretrained,Qwen2ForCausalLM,Original,bfloat16,TRUE,apache-2.0,0,50,TRUE,ff3a49fac17555b8dfc4db6709f480cc8f16a9fe,TRUE,TRUE,2024-06-09,2024-05-31,FALSE,TRUE,Qwen/Qwen2-0.5B,https://huggingface.co/Qwen/Qwen2-0.5B -🟢,microsoft/phi-1_5,7.06,20.33,0.2,7.47,0.34,1.13,0.01,2.35,0.27,3.39,0.34,7.68,0.17,🟢 pretrained,PhiForCausalLM,Original,float16,TRUE,mit,1,1295,TRUE,675aa382d814580b22651a30acb1a585d7c25963,TRUE,TRUE,2024-06-09,2023-09-10,FALSE,TRUE,microsoft/phi-1_5,https://huggingface.co/microsoft/phi-1_5 +🟢,microsoft/phi-1_5,7.06,20.33,0.2,7.47,0.34,1.13,0.01,2.35,0.27,3.39,0.34,7.68,0.17,🟢 pretrained,PhiForCausalLM,Original,float16,TRUE,mit,1,1296,TRUE,675aa382d814580b22651a30acb1a585d7c25963,TRUE,TRUE,2024-06-09,2023-09-10,FALSE,TRUE,microsoft/phi-1_5,https://huggingface.co/microsoft/phi-1_5 🟢,google/recurrentgemma-2b,6.94,30.02,0.3,5.01,0.32,1.66,0.02,0,0.25,2.94,0.34,1.99,0.12,🟢 pretrained,RecurrentGemmaForCausalLM,Original,bfloat16,TRUE,gemma,2,89,TRUE,195f13c55b371fc721eda0662c00c64642c70e17,TRUE,TRUE,2024-06-13,2024-04-06,FALSE,TRUE,google/recurrentgemma-2b,https://huggingface.co/google/recurrentgemma-2b 🟢,databricks/dolly-v1-6b,6.89,22.24,0.22,4.78,0.32,1.36,0.01,1.9,0.26,8.12,0.4,2.95,0.13,🟢 pretrained,GPTJForCausalLM,Original,bfloat16,TRUE,cc-by-nc-4.0,6,309,TRUE,c9a85b3a322b402e20c839c702c725afe0cb454d,TRUE,TRUE,2024-06-12,2023-03-23,FALSE,TRUE,databricks/dolly-v1-6b,https://huggingface.co/databricks/dolly-v1-6b 🔶,togethercomputer/GPT-JT-6B-v1,6.83,20.61,0.21,7.32,0.33,0.76,0.01,1.45,0.26,3.87,0.37,6.95,0.16,🔶 fine-tuned on domain-specific datasets,GPTJForCausalLM,Original,float16,TRUE,apache-2.0,6,302,TRUE,f34aa35f906895602c1f86f5685e598afdea8051,TRUE,TRUE,2024-06-12,2022-11-24,FALSE,TRUE,togethercomputer/GPT-JT-6B-v1,https://huggingface.co/togethercomputer/GPT-JT-6B-v1 @@ -201,12 +201,12 @@ t,model,average,ifeval,ifeval_raw,bbh,bbh_raw,math_lvl_5,math_lvl_5_raw,gpqa,gpq 🟢,EleutherAI/pythia-12b,5.93,24.71,0.25,4.99,0.32,0.91,0.01,0,0.25,3.79,0.36,1.21,0.11,🟢 pretrained,GPTNeoXForCausalLM,Original,float16,TRUE,apache-2.0,12,129,TRUE,35c9d7f32fbb108fb8b5bdd574eb03369d1eed49,TRUE,TRUE,2024-06-12,2023-02-28,FALSE,TRUE,EleutherAI/pythia-12b,https://huggingface.co/EleutherAI/pythia-12b 🟢,EleutherAI/pythia-6.9b,5.85,22.81,0.23,5.88,0.32,0.76,0.01,0.22,0.25,3.81,0.36,1.63,0.11,🟢 pretrained,GPTNeoXForCausalLM,Original,float16,TRUE,apache-2.0,6,41,TRUE,f271943e880e60c0c715fd10e4dc74ec4e31eb44,TRUE,TRUE,2024-06-12,2023-02-14,FALSE,TRUE,EleutherAI/pythia-6.9b,https://huggingface.co/EleutherAI/pythia-6.9b 🟢,openai-community/gpt2-medium,5.81,22.08,0.22,2.72,0.31,0.23,0,1.68,0.26,6.16,0.39,2.02,0.12,🟢 pretrained,GPT2LMHeadModel,Original,bfloat16,TRUE,mit,0,134,TRUE,6dcaa7a952f72f9298047fd5137cd6e4f05f41da,TRUE,TRUE,2024-06-12,2022-03-02,FALSE,TRUE,openai-community/gpt2-medium,https://huggingface.co/openai-community/gpt2-medium -🟢,google/gemma-2-9b,5.67,24.73,0.25,5.05,0.32,0.15,0,0,0.24,2.58,0.36,1.51,0.11,🟢 pretrained,Gemma2ForCausalLM,Original,bfloat16,TRUE,gemma,9,442,TRUE,beb0c08e9eeb0548f3aca2ac870792825c357b7d,TRUE,TRUE,2024-07-11,2024-06-24,FALSE,TRUE,google/gemma-2-9b,https://huggingface.co/google/gemma-2-9b +🟢,google/gemma-2-9b,5.67,24.73,0.25,5.05,0.32,0.15,0,0,0.24,2.58,0.36,1.51,0.11,🟢 pretrained,Gemma2ForCausalLM,Original,bfloat16,TRUE,gemma,9,445,TRUE,beb0c08e9eeb0548f3aca2ac870792825c357b7d,TRUE,TRUE,2024-07-11,2024-06-24,FALSE,TRUE,google/gemma-2-9b,https://huggingface.co/google/gemma-2-9b 🔶,togethercomputer/RedPajama-INCITE-Instruct-3B-v1,5.66,21.24,0.21,4.51,0.31,0.6,0.01,0,0.25,6.41,0.39,1.22,0.11,🔶 fine-tuned on domain-specific datasets,GPTNeoXForCausalLM,Original,float16,TRUE,apache-2.0,3,91,TRUE,0c66778ee09a036886741707733620b91057909a,TRUE,TRUE,2024-06-12,2023-05-05,FALSE,TRUE,togethercomputer/RedPajama-INCITE-Instruct-3B-v1,https://huggingface.co/togethercomputer/RedPajama-INCITE-Instruct-3B-v1 🟢,EleutherAI/pythia-160m,5.62,18.16,0.18,2.2,0.3,0.23,0,1.12,0.26,10.68,0.42,1.33,0.11,🟢 pretrained,GPTNeoXForCausalLM,Original,float16,TRUE,apache-2.0,0,21,TRUE,50f5173d932e8e61f858120bcb800b97af589f46,TRUE,TRUE,2024-06-09,2023-02-08,FALSE,TRUE,EleutherAI/pythia-160m,https://huggingface.co/EleutherAI/pythia-160m 🔶,databricks/dolly-v2-7b,5.57,20.1,0.2,5.45,0.32,0.98,0.01,2.46,0.27,2.78,0.36,1.66,0.11,🔶 fine-tuned on domain-specific datasets,GPTNeoXForCausalLM,Original,bfloat16,TRUE,mit,7,146,TRUE,d632f0c8b75b1ae5b26b250d25bfba4e99cb7c6f,TRUE,TRUE,2024-06-12,2023-04-13,FALSE,TRUE,databricks/dolly-v2-7b,https://huggingface.co/databricks/dolly-v2-7b 💬,Qwen/Qwen1.5-0.5B-Chat,5.56,18.07,0.18,4.32,0.32,0,0,2.57,0.27,6.06,0.38,2.36,0.12,"💬 chat models (RLHF, DPO, IFT, ...)",Qwen2ForCausalLM,Original,bfloat16,TRUE,other,0,71,TRUE,4d14e384a4b037942bb3f3016665157c8bcb70ea,TRUE,TRUE,2024-06-12,2024-01-31,TRUE,TRUE,Qwen/Qwen1.5-0.5B-Chat,https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat -🟢,microsoft/phi-1,5.52,20.68,0.21,4.27,0.31,0.68,0.01,2.01,0.27,3.7,0.35,1.8,0.12,🟢 pretrained,PhiForCausalLM,Original,bfloat16,TRUE,mit,1,198,TRUE,b9ac0e6d78d43970ecf88e9e0154b3a7da20ed89,TRUE,TRUE,2024-06-13,2023-09-10,FALSE,TRUE,microsoft/phi-1,https://huggingface.co/microsoft/phi-1 +🟢,microsoft/phi-1,5.52,20.68,0.21,4.27,0.31,0.68,0.01,2.01,0.27,3.7,0.35,1.8,0.12,🟢 pretrained,PhiForCausalLM,Original,bfloat16,TRUE,mit,1,199,TRUE,b9ac0e6d78d43970ecf88e9e0154b3a7da20ed89,TRUE,TRUE,2024-06-13,2023-09-10,FALSE,TRUE,microsoft/phi-1,https://huggingface.co/microsoft/phi-1 🟢,openai-community/gpt2-large,5.48,20.48,0.2,3.25,0.31,0.68,0.01,1.23,0.26,5.66,0.38,1.58,0.11,🟢 pretrained,GPT2LMHeadModel,Original,bfloat16,TRUE,mit,0,243,TRUE,32b71b12589c2f8d625668d2335a01cac3249519,TRUE,TRUE,2024-06-12,2022-03-02,FALSE,TRUE,openai-community/gpt2-large,https://huggingface.co/openai-community/gpt2-large 🟢,togethercomputer/RedPajama-INCITE-7B-Base,5.46,20.82,0.21,5.09,0.32,0.98,0.01,0.67,0.26,3.02,0.36,2.19,0.12,🟢 pretrained,GPTNeoXForCausalLM,Original,float16,TRUE,apache-2.0,7,93,TRUE,78f7e482443971f4873ba3239f0ac810a367833b,TRUE,TRUE,2024-06-12,2023-05-04,FALSE,TRUE,togethercomputer/RedPajama-INCITE-7B-Base,https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base 🔶,databricks/dolly-v2-3b,5.45,22.47,0.22,3.32,0.31,0.6,0.01,1.45,0.26,3.22,0.33,1.61,0.11,🔶 fine-tuned on domain-specific datasets,GPTNeoXForCausalLM,Original,bfloat16,TRUE,mit,3,284,TRUE,f6c9be08f16fe4d3a719bee0a4a7c7415b5c65df,TRUE,TRUE,2024-06-12,2023-04-13,FALSE,TRUE,databricks/dolly-v2-3b,https://huggingface.co/databricks/dolly-v2-3b @@ -220,7 +220,7 @@ t,model,average,ifeval,ifeval_raw,bbh,bbh_raw,math_lvl_5,math_lvl_5_raw,gpqa,gpq 🟢,Qwen/Qwen1.5-0.5B,5.14,17.06,0.17,5.04,0.32,0.45,0,0.56,0.25,4.3,0.36,3.41,0.13,🟢 pretrained,Qwen2ForCausalLM,Original,bfloat16,TRUE,other,0,131,TRUE,8f445e3628f3500ee69f24e1303c9f10f5342a39,TRUE,TRUE,2024-06-13,2024-01-22,FALSE,TRUE,Qwen/Qwen1.5-0.5B,https://huggingface.co/Qwen/Qwen1.5-0.5B 🟢,EleutherAI/pythia-410m,5.11,21.95,0.22,2.72,0.3,0.3,0,1.23,0.26,3.06,0.36,1.42,0.11,🟢 pretrained,GPTNeoXForCausalLM,Original,float16,TRUE,apache-2.0,0,20,TRUE,9879c9b5f8bea9051dcb0e68dff21493d67e9d4f,TRUE,TRUE,2024-06-09,2023-02-13,FALSE,TRUE,EleutherAI/pythia-410m,https://huggingface.co/EleutherAI/pythia-410m 🟢,tiiuae/falcon-7b,5.1,18.21,0.18,5.96,0.33,0.53,0.01,0,0.24,4.5,0.38,1.39,0.11,🟢 pretrained,FalconForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,1054,TRUE,898df1396f35e447d5fe44e0a3ccaaaa69f30d36,TRUE,TRUE,2024-06-09,2023-04-24,FALSE,TRUE,tiiuae/falcon-7b,https://huggingface.co/tiiuae/falcon-7b -💬,tiiuae/falcon-7b-instruct,5.02,19.69,0.2,4.82,0.32,0.6,0.01,0,0.25,3.25,0.36,1.73,0.12,"💬 chat models (RLHF, DPO, IFT, ...)",FalconForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,884,TRUE,cf4b3c42ce2fdfe24f753f0f0d179202fea59c99,TRUE,TRUE,2024-06-09,2023-04-25,FALSE,TRUE,tiiuae/falcon-7b-instruct,https://huggingface.co/tiiuae/falcon-7b-instruct +💬,tiiuae/falcon-7b-instruct,5.02,19.69,0.2,4.82,0.32,0.6,0.01,0,0.25,3.25,0.36,1.73,0.12,"💬 chat models (RLHF, DPO, IFT, ...)",FalconForCausalLM,Original,bfloat16,TRUE,apache-2.0,7,886,TRUE,cf4b3c42ce2fdfe24f753f0f0d179202fea59c99,TRUE,TRUE,2024-06-09,2023-04-25,FALSE,TRUE,tiiuae/falcon-7b-instruct,https://huggingface.co/tiiuae/falcon-7b-instruct 🟢,openai-community/gpt2-xl,4.98,20.39,0.2,2.58,0.3,0.3,0,1.12,0.26,4.04,0.37,1.46,0.11,🟢 pretrained,GPT2LMHeadModel,Original,bfloat16,TRUE,mit,1,295,TRUE,15ea56dee5df4983c59b2538573817e1667135e2,TRUE,TRUE,2024-06-12,2022-03-02,FALSE,TRUE,openai-community/gpt2-xl,https://huggingface.co/openai-community/gpt2-xl 🔶,togethercomputer/GPT-NeoXT-Chat-Base-20B,4.94,18.3,0.18,6.83,0.33,1.13,0.01,0,0.25,1.76,0.35,1.61,0.11,🔶 fine-tuned on domain-specific datasets,GPTNeoXForCausalLM,Original,float16,TRUE,apache-2.0,20,693,TRUE,d386708e84d862a65f7d2b4989f64750cb657227,TRUE,TRUE,2024-06-12,2023-03-03,FALSE,TRUE,togethercomputer/GPT-NeoXT-Chat-Base-20B,https://huggingface.co/togethercomputer/GPT-NeoXT-Chat-Base-20B 🔶,togethercomputer/RedPajama-INCITE-Chat-3B-v1,4.75,16.52,0.17,5.16,0.32,0.3,0,0,0.24,5.09,0.37,1.41,0.11,🔶 fine-tuned on domain-specific datasets,GPTNeoXForCausalLM,Original,float16,TRUE,apache-2.0,3,147,TRUE,f0e0995eba801096ed04cb87931d96a8316871af,TRUE,TRUE,2024-06-13,2023-05-05,FALSE,TRUE,togethercomputer/RedPajama-INCITE-Chat-3B-v1,https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1