{ "_name_or_path": "/home/gangda/workspace/czl/swebench/outputs_data/train_output/7B/output_0107/6epoch_768ins_16bit_128k/merged", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "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": 151665, "rms_norm_eps": 1e-06, "rope_scaling": { "factor": 4.0, "rope_type": "linear", "type": "linear" }, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.46.3", "unsloth_fixed": true, "unsloth_version": "2024.11.9", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064 }