xinlai/DeepSeekMath-RL-Step-DPO
236
1{2 "_from_model_config": true,3 "bos_token_id": 100000,4 "eos_token_id": 100001,5 "transformers_version": "4.40.0",6 "use_cache": false7}8 1{2 "_from_model_config": true,3 "bos_token_id": 100000,4 "eos_token_id": 100001,5 "transformers_version": "4.40.0",6 "use_cache": false7}8