{ "_name_or_path": "/home/wangzefan/data/verl_scalerl/checkpoints/scalerl/Qwen2.5Base_VRAccFilter0.03-0.97_clip0.27_WebInst_b768_mbs192_lr1e-6_r3_n8_e100-4node/global_step_180/actor/huggingface_model", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "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": 28, "num_key_value_heads": 4, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": 131072, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 152064 }