{ "architectures": [ "Qwen3VLModel" ], "dtype": "bfloat16", "image_token_id": 151655, "model_type": "qwen3_vl", "text_config": { "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": 4096, "initializer_range": 0.02, "intermediate_size": 12288, "max_position_embeddings": 262144, "model_type": "qwen3_vl_text", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "pad_token_id": null, "rms_norm_eps": 1e-06, "rope_parameters": { "mrope_interleaved": true, "mrope_section": [ 24, 20, 20 ], "rope_theta": 5000000, "rope_type": "default" }, "use_cache": true, "vocab_size": 151936 }, "tie_word_embeddings": false, "transformers_version": "5.8.0", "video_token_id": 151656, "vision_config": { "deepstack_visual_indexes": [ 8, 16, 24 ], "depth": 27, "dtype": "bfloat16", "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 4304, "model_type": "qwen3_vl_vision", "num_heads": 16, "num_position_embeddings": 2304, "out_hidden_size": 4096, "patch_size": 16, "spatial_merge_size": 2, "temporal_patch_size": 2 }, "vision_end_token_id": 151653, "vision_start_token_id": 151652, "ideogram_fp8_weight_only": true, "quantization_config": { "add_skip_keys": false, "dequantize_fp32": true, "dynamic_loss_threshold": -1, "group_size": -1, "hadamard_group_size": 128, "is_integer": false, "is_training": false, "modules_dtype_dict": {}, "modules_quant_config": {}, "modules_to_not_convert": [ "language_model.embed_tokens.weight", "language_model.layers.0.input_layernorm.weight", "language_model.layers.0.post_attention_layernorm.weight", "language_model.layers.0.self_attn.k_norm.weight", "language_model.layers.0.self_attn.q_norm.weight", "language_model.layers.1.input_layernorm.weight", "language_model.layers.1.post_attention_layernorm.weight", "language_model.layers.1.self_attn.k_norm.weight", "language_model.layers.1.self_attn.q_norm.weight", "language_model.layers.10.input_layernorm.weight", "language_model.layers.10.post_attention_layernorm.weight", "language_model.layers.10.self_attn.k_norm.weight", "language_model.layers.10.self_attn.q_norm.weight", "language_model.layers.11.input_layernorm.weight", "language_model.layers.11.post_attention_layernorm.weight", "language_model.layers.11.self_attn.k_norm.weight", "language_model.layers.11.self_attn.q_norm.weight", "language_model.layers.12.input_layernorm.weight", "language_model.layers.12.post_attention_layernorm.weight", "language_model.layers.12.self_attn.k_norm.weight", "language_model.layers.12.self_attn.q_norm.weight", "language_model.layers.13.input_layernorm.weight", "language_model.layers.13.post_attention_layernorm.weight", "language_model.layers.13.self_attn.k_norm.weight", "language_model.layers.13.self_attn.q_norm.weight", "language_model.layers.14.input_layernorm.weight", "language_model.layers.14.post_attention_layernorm.weight", "language_model.layers.14.self_attn.k_norm.weight", "language_model.layers.14.self_attn.q_norm.weight", "language_model.layers.15.input_layernorm.weight", "language_model.layers.15.post_attention_layernorm.weight", "language_model.layers.15.self_attn.k_norm.weight", "language_model.layers.15.self_attn.q_norm.weight", "language_model.layers.16.input_layernorm.weight", "language_model.layers.16.post_attention_layernorm.weight", "language_model.layers.16.self_attn.k_norm.weight", "language_model.layers.16.self_attn.q_norm.weight", "language_model.layers.17.input_layernorm.weight", "language_model.layers.17.post_attention_layernorm.weight", "language_model.layers.17.self_attn.k_norm.weight", "language_model.layers.17.self_attn.q_norm.weight", "language_model.layers.18.input_layernorm.weight", "language_model.layers.18.post_attention_layernorm.weight", "language_model.layers.18.self_attn.k_norm.weight", "language_model.layers.18.self_attn.q_norm.weight", "language_model.layers.19.input_layernorm.weight", "language_model.layers.19.post_attention_layernorm.weight", "language_model.layers.19.self_attn.k_norm.weight", "language_model.layers.19.self_attn.q_norm.weight", "language_model.layers.2.input_layernorm.weight", "language_model.layers.2.post_attention_layernorm.weight", "language_model.layers.2.self_attn.k_norm.weight", "language_model.layers.2.self_attn.q_norm.weight", "language_model.layers.20.input_layernorm.weight", "language_model.layers.20.post_attention_layernorm.weight", "language_model.layers.20.self_attn.k_norm.weight", "language_model.layers.20.self_attn.q_norm.weight", "language_model.layers.21.input_layernorm.weight", "language_model.layers.21.post_attention_layernorm.weight", "language_model.layers.21.self_attn.k_norm.weight", "language_model.layers.21.self_attn.q_norm.weight", "language_model.layers.22.input_layernorm.weight", "language_model.layers.22.post_attention_layernorm.weight", "language_model.layers.22.self_attn.k_norm.weight", "language_model.layers.22.self_attn.q_norm.weight", "language_model.layers.23.input_layernorm.weight", "language_model.layers.23.post_attention_layernorm.weight", "language_model.layers.23.self_attn.k_norm.weight", "language_model.layers.23.self_attn.q_norm.weight", "language_model.layers.24.input_layernorm.weight", "language_model.layers.24.post_attention_layernorm.weight", "language_model.layers.24.self_attn.k_norm.weight", "language_model.layers.24.self_attn.q_norm.weight", "language_model.layers.25.input_layernorm.weight", "language_model.layers.25.post_attention_layernorm.weight", "language_model.layers.25.self_attn.k_norm.weight", "language_model.layers.25.self_attn.q_norm.weight", "language_model.layers.26.input_layernorm.weight", "language_model.layers.26.post_attention_layernorm.weight", "language_model.layers.26.self_attn.k_norm.weight", "language_model.layers.26.self_attn.q_norm.weight", "language_model.layers.27.input_layernorm.weight", "language_model.layers.27.post_attention_layernorm.weight", "language_model.layers.27.self_attn.k_norm.weight", "language_model.layers.27.self_attn.q_norm.weight", "language_model.layers.28.input_layernorm.weight", "language_model.layers.28.post_attention_layernorm.weight", "language_model.layers.28.self_attn.k_norm.weight", "language_model.layers.28.self_attn.q_norm.weight", "language_model.layers.29.input_layernorm.weight", "language_model.layers.29.post_attention_layernorm.weight", "language_model.layers.29.self_attn.k_norm.weight", "language_model.layers.29.self_attn.q_norm.weight", "language_model.layers.3.input_layernorm.weight", "language_model.layers.3.post_attention_layernorm.weight", "language_model.layers.3.self_attn.k_norm.weight", "language_model.layers.3.self_attn.q_norm.weight", "language_model.layers.30.input_layernorm.weight", "language_model.layers.30.post_attention_layernorm.weight", "language_model.layers.30.self_attn.k_norm.weight", "language_model.layers.30.self_attn.q_norm.weight", "language_model.layers.31.input_layernorm.weight", "language_model.layers.31.post_attention_layernorm.weight", "language_model.layers.31.self_attn.k_norm.weight", "language_model.layers.31.self_attn.q_norm.weight", "language_model.layers.32.input_layernorm.weight", "language_model.layers.32.post_attention_layernorm.weight", "language_model.layers.32.self_attn.k_norm.weight", "language_model.layers.32.self_attn.q_norm.weight", "language_model.layers.33.input_layernorm.weight", "language_model.layers.33.post_attention_layernorm.weight", "language_model.layers.33.self_attn.k_norm.weight", "language_model.layers.33.self_attn.q_norm.weight", "language_model.layers.34.input_layernorm.weight", "language_model.layers.34.post_attention_layernorm.weight", "language_model.layers.34.self_attn.k_norm.weight", "language_model.layers.34.self_attn.q_norm.weight", "language_model.layers.35.input_layernorm.weight", "language_model.layers.35.post_attention_layernorm.weight", "language_model.layers.35.self_attn.k_norm.weight", "language_model.layers.35.self_attn.q_norm.weight", "language_model.layers.4.input_layernorm.weight", "language_model.layers.4.post_attention_layernorm.weight", "language_model.layers.4.self_attn.k_norm.weight", "language_model.layers.4.self_attn.q_norm.weight", "language_model.layers.5.input_layernorm.weight", "language_model.layers.5.post_attention_layernorm.weight", "language_model.layers.5.self_attn.k_norm.weight", "language_model.layers.5.self_attn.q_norm.weight", "language_model.layers.6.input_layernorm.weight", "language_model.layers.6.post_attention_layernorm.weight", "language_model.layers.6.self_attn.k_norm.weight", "language_model.layers.6.self_attn.q_norm.weight", "language_model.layers.7.input_layernorm.weight", "language_model.layers.7.post_attention_layernorm.weight", "language_model.layers.7.self_attn.k_norm.weight", "language_model.layers.7.self_attn.q_norm.weight", "language_model.layers.8.input_layernorm.weight", "language_model.layers.8.post_attention_layernorm.weight", "language_model.layers.8.self_attn.k_norm.weight", "language_model.layers.8.self_attn.q_norm.weight", "language_model.layers.9.input_layernorm.weight", "language_model.layers.9.post_attention_layernorm.weight", "language_model.layers.9.self_attn.k_norm.weight", "language_model.layers.9.self_attn.q_norm.weight", "language_model.norm.weight", "visual.blocks.0.norm1.weight", "visual.blocks.0.norm2.weight", "visual.blocks.1.norm1.weight", "visual.blocks.1.norm2.weight", "visual.blocks.10.norm1.weight", "visual.blocks.10.norm2.weight", "visual.blocks.11.norm1.weight", "visual.blocks.11.norm2.weight", "visual.blocks.12.norm1.weight", "visual.blocks.12.norm2.weight", "visual.blocks.13.norm1.weight", "visual.blocks.13.norm2.weight", "visual.blocks.14.norm1.weight", "visual.blocks.14.norm2.weight", "visual.blocks.15.norm1.weight", "visual.blocks.15.norm2.weight", "visual.blocks.16.norm1.weight", "visual.blocks.16.norm2.weight", "visual.blocks.17.norm1.weight", "visual.blocks.17.norm2.weight", "visual.blocks.18.norm1.weight", "visual.blocks.18.norm2.weight", "visual.blocks.19.norm1.weight", "visual.blocks.19.norm2.weight", "visual.blocks.2.norm1.weight", "visual.blocks.2.norm2.weight", "visual.blocks.20.norm1.weight", "visual.blocks.20.norm2.weight", "visual.blocks.21.norm1.weight", "visual.blocks.21.norm2.weight", "visual.blocks.22.norm1.weight", "visual.blocks.22.norm2.weight", "visual.blocks.23.norm1.weight", "visual.blocks.23.norm2.weight", "visual.blocks.24.norm1.weight", "visual.blocks.24.norm2.weight", "visual.blocks.25.norm1.weight", "visual.blocks.25.norm2.weight", "visual.blocks.26.norm1.weight", "visual.blocks.26.norm2.weight", "visual.blocks.3.norm1.weight", "visual.blocks.3.norm2.weight", "visual.blocks.4.norm1.weight", "visual.blocks.4.norm2.weight", "visual.blocks.5.norm1.weight", "visual.blocks.5.norm2.weight", "visual.blocks.6.norm1.weight", "visual.blocks.6.norm2.weight", "visual.blocks.7.norm1.weight", "visual.blocks.7.norm2.weight", "visual.blocks.8.norm1.weight", "visual.blocks.8.norm2.weight", "visual.blocks.9.norm1.weight", "visual.blocks.9.norm2.weight", "visual.deepstack_merger_list.0.norm.weight", "visual.deepstack_merger_list.1.norm.weight", "visual.deepstack_merger_list.2.norm.weight", "visual.merger.norm.weight", "visual.patch_embed.proj.weight", "visual.pos_embed.weight" ], "modules_to_not_use_matmul": [], "non_blocking": false, "quant_conv": false, "quant_embedding": false, "quant_method": "sdnq", "quantization_device": null, "quantized_matmul_dtype": null, "return_device": null, "sdnq_version": "0.2.0", "svd_rank": 32, "svd_steps": 8, "use_dynamic_quantization": false, "use_grad_ckpt": true, "use_hadamard": false, "use_quantized_matmul": false, "use_quantized_matmul_conv": false, "use_static_quantization": true, "use_stochastic_rounding": false, "use_svd": false, "weights_dtype": "float8_e4m3fn" } }