| { | |
| "_moe_implementation": "fused", | |
| "_name_or_path": "/opt/tiger/.cache/src_model/huggingface", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "attention_out_bias": true, | |
| "bos_token_id": 151644, | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.01613743060919757, | |
| "intermediate_size": 27648, | |
| "layer_norm_eps": null, | |
| "max_position_embeddings": 32768, | |
| "mlp_bias": false, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 151643, | |
| "resid_pdrop": 0.0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "factor": 1, | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.47.1", | |
| "use_cache": true, | |
| "vocab_size": 152064 | |
| } | |