| { |
| "architectures": [ |
| "Qwen3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "dtype": "bfloat16", |
| "eos_token_id": 151645, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 9728, |
| "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": { |
| "add_skip_keys": false, |
| "dequantize_fp32": false, |
| "group_size": 0, |
| "is_integer": true, |
| "is_training": false, |
| "modules_dtype_dict": {}, |
| "modules_to_not_convert": [ |
| ".x_embedder", |
| ".img_in", |
| "patch_embed", |
| ".condition_embedder", |
| "time_text_embed", |
| "lm_head", |
| ".time_embed", |
| ".txt_out", |
| "patch_emb", |
| "multi_modal_projector", |
| ".final_layer", |
| ".vid_in", |
| ".context_embedder", |
| ".proj_out", |
| ".norm_out", |
| ".txt_in", |
| ".emb_in", |
| ".emb_out", |
| "patch_embedding", |
| "wte", |
| ".vid_out", |
| "lm_head.weight", |
| ".img_out" |
| ], |
| "non_blocking": false, |
| "quant_conv": false, |
| "quant_method": "sdnq", |
| "quantization_device": null, |
| "quantized_matmul_dtype": null, |
| "return_device": null, |
| "svd_rank": 32, |
| "svd_steps": 8, |
| "use_grad_ckpt": true, |
| "use_quantized_matmul": false, |
| "use_quantized_matmul_conv": false, |
| "use_static_quantization": true, |
| "use_stochastic_rounding": false, |
| "use_svd": true, |
| "weights_dtype": "uint4" |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000, |
| "sliding_window": null, |
| "tie_word_embeddings": true, |
| "transformers_version": "4.57.1", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| } |
|
|