| { | |
| "_name_or_path": "/apdcephfs/share_302520718/share_info/peisongwang/saved_models/saved_models/Qwen2.5-Math-7B-YARN_sft_qwen2.5_math_7B_base_0127_new_veri_3k_raw_20250204_022818/checkpoint-412", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128245, | |
| "eos_token": "<|im_end|>", | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 4096, | |
| "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": null, | |
| "rope_theta": 10000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.3", | |
| "use_cache": false, | |
| "use_mrope": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151666 | |
| } | |