| { | |
| "architectures": [ | |
| "Qwen2Model" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 27648, | |
| "max_position_embeddings": 131072, | |
| "max_window_layers": 64, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "quantization_config": { | |
| "modules_to_not_convert": null, | |
| "quant_method": "torchao", | |
| "quant_type": { | |
| "default": { | |
| "_data": { | |
| "group_size": 128, | |
| "layout": { | |
| "_data": {}, | |
| "_type": "Int4CPULayout", | |
| "_version": 1 | |
| }, | |
| "set_inductor_config": true, | |
| "use_hqq": false, | |
| "zero_point_domain": { | |
| "_data": "NONE", | |
| "_type": "ZeroPointDomain" | |
| } | |
| }, | |
| "_type": "Int4WeightOnlyConfig", | |
| "_version": 1 | |
| } | |
| }, | |
| "quant_type_kwargs": {} | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 131072, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.3", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |