| { | |
| "_name_or_path": "/juice5/scr5/nlp/crfm/human-feedback/models/selfinstruct/reward_model_noised_multi_v1/reward_model_noised_multi_v1_p0.5", | |
| "architectures": [ | |
| "RewardModel" | |
| ], | |
| "backbone_model_name_or_path": "/juice5/scr5/nlp/crfm/human-feedback/models/selfinstruct/sft_v6_llama_7b_regen_v7_3ep", | |
| "model_type": "reward_model", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.29.2" | |
| } | |