{ "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12288, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 40960, "max_window_layers": 36, "model_type": "qwen3", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "quantization_config": { "include_input_output_embeddings": false, "modules_to_not_convert": null, "quant_method": "torchao", "quant_type": { "default": { "_data": { "base_config": { "_data": { "group_size": 128, "int4_choose_qparams_algorithm": { "_data": "TINYGEMM", "_type": "Int4ChooseQParamsAlgorithm" }, "int4_packing_format": { "_data": "PLAIN", "_type": "Int4PackingFormat" }, "layout": { "_data": { "inner_k_tiles": 8 }, "_type": "TensorCoreTiledLayout", "_version": 1 }, "preserve_zero": null, "set_inductor_config": true, "use_hqq": false, "zero_point_domain": { "_data": "NONE", "_type": "ZeroPointDomain" } }, "_type": "Int4WeightOnlyConfig", "_version": 2 }, "scale_search_space_size": 20, "step": "prepare_for_loading" }, "_type": "AWQConfig", "_version": 1 } }, "quant_type_kwargs": {}, "untie_embedding_weights": false }, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.55.4", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }