GTAlign/Qwen2.5-3B-Math-140step

1{2  "architectures": [3    "Qwen2ForCausalLM"4  ],5  "attention_dropout": 0.0,6  "eos_token_id": 151645,7  "hidden_act": "silu",8  "hidden_size": 2048,9  "initializer_range": 0.02,10  "intermediate_size": 11008,11  "max_position_embeddings": 32768,12  "max_window_layers": 70,13  "model_type": "qwen2",14  "num_attention_heads": 16,15  "num_hidden_layers": 36,16  "num_key_value_heads": 2,17  "pad_token_id": 151643,18  "rms_norm_eps": 1e-06,19  "rope_scaling": null,20  "rope_theta": 1000000.0,21  "sliding_window": 32768,22  "tie_word_embeddings": true,23  "torch_dtype": "bfloat16",24  "transformers_version": "4.51.1",25  "use_cache": true,26  "use_sliding_window": false,27  "vocab_size": 15193628}29