init

allenai · Feb 8, 2024 · 62175b2 · 62175b2
1 parent 5a8f218
commit 62175b2
Show file tree

Hide file tree

Showing 3 changed files with 476 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -45,6 +45,7 @@ python scripts/run_rm.py --model=weqweasdas/hh_rlhf_rm_open_llama_3b --chat_temp
 python scripts/run_rm.py --model=llm-blender/PairRM-hf --direct_load
 python scripts/run_rm.py --model=berkeley-nest/Starling-RM-7B-alpha --tokenizer=meta-llama/Llama-2-7b-chat-hf --chat_template=llama-2 --direct_load --batch_size=16
 python scripts/run_rm.py --model=stanfordnlp/SteamSHP-flan-t5-xl --direct_load --batch_size=32
+python scripts/run_rm.py --model=PKU-Alignment/beaver-7b-v1.0-reward --chat_template=pku-align --direct_load --batch_size=32
 ```
 
 And for DPO: