{ "_name_or_path": "/inspire/hdd/ws-f4d69b29-e0a5-44e6-bd92-acf4de9990f0/public-project/zhuwenhong-240108120129/model/Deepseek-qwen2.5-7B-pre1-longcot", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 131072, "max_window_layers": 28, "model_type": "qwen2", "num_attention_heads": 28, "num_hidden_layers": 29, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.45.0", "use_cache": false, "use_mrope": false, "use_sliding_window": false, "vocab_size": 152064 }