{ "architectures": [ "Qwen3_5TextModel" ], "attention_bias": false, "attention_dropout": 0.0, "attn_output_gate": true, "bos_token_id": null, "dtype": "bfloat16", "eos_token_id": 248044, "full_attention_interval": 4, "head_dim": 256, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12288, "layer_types": [ "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention" ], "linear_conv_kernel_dim": 4, "linear_key_head_dim": 128, "linear_num_key_heads": 16, "linear_num_value_heads": 32, "linear_value_head_dim": 128, "mamba_ssm_dtype": "float32", "max_position_embeddings": 262144, "mlp_only_layers": [], "model_type": "qwen3_5_text", "mtp_num_hidden_layers": 1, "mtp_use_dedicated_embeddings": false, "num_attention_heads": 16, "num_hidden_layers": 32, "num_key_value_heads": 4, "pad_token_id": null, "partial_rotary_factor": 0.25, "quantization_config": { "add_skip_keys": true, "codebook_steps": 24, "dequantize_fp32": false, "dynamic_loss_threshold": 0.01, "group_size": 0, "hadamard_group_size": 256, "is_integer": true, "is_training": false, "is_unsigned": true, "minimum_allowed_channel_size": 32, "minimum_allowed_numel": 16384, "modules_dtype_dict": { "uint4": [ "layers.0.linear_attn.in_proj_a.weight", "layers.0.linear_attn.in_proj_b.weight", "layers.0.linear_attn.in_proj_qkv.weight", "layers.0.linear_attn.in_proj_z.weight", "layers.0.linear_attn.out_proj.weight", "layers.0.mlp.down_proj.weight", "layers.0.mlp.gate_proj.weight", "layers.0.mlp.up_proj.weight", "layers.1.linear_attn.in_proj_a.weight", "layers.1.linear_attn.in_proj_b.weight", "layers.1.linear_attn.in_proj_qkv.weight", "layers.1.linear_attn.in_proj_z.weight", "layers.1.linear_attn.out_proj.weight", "layers.1.mlp.down_proj.weight", "layers.1.mlp.gate_proj.weight", "layers.1.mlp.up_proj.weight", "layers.2.linear_attn.in_proj_a.weight", "layers.2.linear_attn.in_proj_b.weight", "layers.2.linear_attn.in_proj_qkv.weight", "layers.2.linear_attn.in_proj_z.weight", "layers.2.linear_attn.out_proj.weight", "layers.2.mlp.down_proj.weight", "layers.2.mlp.gate_proj.weight", "layers.2.mlp.up_proj.weight", "layers.3.mlp.down_proj.weight", "layers.3.mlp.gate_proj.weight", "layers.3.mlp.up_proj.weight", "layers.3.self_attn.k_proj.weight", "layers.3.self_attn.o_proj.weight", "layers.3.self_attn.q_proj.weight", "layers.3.self_attn.v_proj.weight", "layers.4.linear_attn.in_proj_a.weight", "layers.4.linear_attn.in_proj_b.weight", "layers.4.linear_attn.in_proj_qkv.weight", "layers.4.linear_attn.in_proj_z.weight", "layers.4.linear_attn.out_proj.weight", "layers.4.mlp.down_proj.weight", "layers.4.mlp.gate_proj.weight", "layers.4.mlp.up_proj.weight", "layers.5.linear_attn.in_proj_a.weight", "layers.5.linear_attn.in_proj_b.weight", "layers.5.linear_attn.in_proj_qkv.weight", "layers.5.linear_attn.in_proj_z.weight", "layers.5.linear_attn.out_proj.weight", "layers.5.mlp.down_proj.weight", "layers.5.mlp.gate_proj.weight", "layers.5.mlp.up_proj.weight", "layers.6.linear_attn.in_proj_a.weight", "layers.6.linear_attn.in_proj_b.weight", "layers.6.linear_attn.in_proj_qkv.weight", "layers.6.linear_attn.in_proj_z.weight", "layers.6.linear_attn.out_proj.weight", "layers.6.mlp.down_proj.weight", "layers.6.mlp.gate_proj.weight", "layers.6.mlp.up_proj.weight", "layers.7.mlp.down_proj.weight", "layers.7.mlp.gate_proj.weight", "layers.7.mlp.up_proj.weight", "layers.7.self_attn.k_proj.weight", "layers.7.self_attn.o_proj.weight", "layers.7.self_attn.q_proj.weight", "layers.7.self_attn.v_proj.weight", "layers.8.linear_attn.in_proj_a.weight", "layers.8.linear_attn.in_proj_b.weight", "layers.8.linear_attn.in_proj_qkv.weight", "layers.8.linear_attn.in_proj_z.weight", "layers.8.linear_attn.out_proj.weight", "layers.8.mlp.down_proj.weight", "layers.8.mlp.gate_proj.weight", "layers.8.mlp.up_proj.weight", "layers.9.linear_attn.in_proj_a.weight", "layers.9.linear_attn.in_proj_b.weight", "layers.9.linear_attn.in_proj_qkv.weight", "layers.9.linear_attn.in_proj_z.weight", "layers.9.linear_attn.out_proj.weight", "layers.9.mlp.down_proj.weight", "layers.9.mlp.gate_proj.weight", "layers.9.mlp.up_proj.weight", "layers.10.linear_attn.in_proj_a.weight", "layers.10.linear_attn.in_proj_b.weight", "layers.10.linear_attn.in_proj_qkv.weight", "layers.10.linear_attn.in_proj_z.weight", "layers.10.linear_attn.out_proj.weight", "layers.10.mlp.down_proj.weight", "layers.10.mlp.gate_proj.weight", "layers.10.mlp.up_proj.weight", "layers.11.mlp.down_proj.weight", "layers.11.mlp.gate_proj.weight", "layers.11.mlp.up_proj.weight", "layers.11.self_attn.k_proj.weight", "layers.11.self_attn.o_proj.weight", "layers.11.self_attn.q_proj.weight", "layers.11.self_attn.v_proj.weight", "layers.12.linear_attn.in_proj_a.weight", "layers.12.linear_attn.in_proj_b.weight", "layers.12.linear_attn.in_proj_qkv.weight", "layers.12.linear_attn.in_proj_z.weight", "layers.12.linear_attn.out_proj.weight", "layers.12.mlp.down_proj.weight", "layers.12.mlp.gate_proj.weight", "layers.12.mlp.up_proj.weight", "layers.13.linear_attn.in_proj_a.weight", "layers.13.linear_attn.in_proj_b.weight", "layers.13.linear_attn.in_proj_qkv.weight", "layers.13.linear_attn.in_proj_z.weight", "layers.13.linear_attn.out_proj.weight", "layers.13.mlp.down_proj.weight", "layers.13.mlp.gate_proj.weight", "layers.13.mlp.up_proj.weight", "layers.14.linear_attn.in_proj_a.weight", "layers.14.linear_attn.in_proj_b.weight", "layers.14.linear_attn.in_proj_qkv.weight", "layers.14.linear_attn.in_proj_z.weight", "layers.14.linear_attn.out_proj.weight", "layers.14.mlp.down_proj.weight", "layers.14.mlp.gate_proj.weight", "layers.14.mlp.up_proj.weight", "layers.15.mlp.down_proj.weight", "layers.15.mlp.gate_proj.weight", "layers.15.mlp.up_proj.weight", "layers.15.self_attn.k_proj.weight", "layers.15.self_attn.o_proj.weight", "layers.15.self_attn.q_proj.weight", "layers.15.self_attn.v_proj.weight", "layers.16.linear_attn.in_proj_a.weight", "layers.16.linear_attn.in_proj_b.weight", "layers.16.linear_attn.in_proj_qkv.weight", "layers.16.linear_attn.in_proj_z.weight", "layers.16.linear_attn.out_proj.weight", "layers.16.mlp.down_proj.weight", "layers.16.mlp.gate_proj.weight", "layers.16.mlp.up_proj.weight", "layers.17.linear_attn.in_proj_a.weight", "layers.17.linear_attn.in_proj_b.weight", "layers.17.linear_attn.in_proj_qkv.weight", "layers.17.linear_attn.in_proj_z.weight", "layers.17.linear_attn.out_proj.weight", "layers.17.mlp.down_proj.weight", "layers.17.mlp.gate_proj.weight", "layers.17.mlp.up_proj.weight", "layers.18.linear_attn.in_proj_a.weight", "layers.18.linear_attn.in_proj_b.weight", "layers.18.linear_attn.in_proj_qkv.weight", "layers.18.linear_attn.in_proj_z.weight", "layers.18.linear_attn.out_proj.weight", "layers.18.mlp.down_proj.weight", "layers.18.mlp.gate_proj.weight", "layers.18.mlp.up_proj.weight", "layers.19.mlp.down_proj.weight", "layers.19.mlp.gate_proj.weight", "layers.19.mlp.up_proj.weight", "layers.19.self_attn.k_proj.weight", "layers.19.self_attn.o_proj.weight", "layers.19.self_attn.q_proj.weight", "layers.19.self_attn.v_proj.weight", "layers.20.linear_attn.in_proj_a.weight", "layers.20.linear_attn.in_proj_b.weight", "layers.20.linear_attn.in_proj_qkv.weight", "layers.20.linear_attn.in_proj_z.weight", "layers.20.linear_attn.out_proj.weight", "layers.20.mlp.down_proj.weight", "layers.20.mlp.gate_proj.weight", "layers.20.mlp.up_proj.weight", "layers.21.linear_attn.in_proj_a.weight", "layers.21.linear_attn.in_proj_b.weight", "layers.21.linear_attn.in_proj_qkv.weight", "layers.21.linear_attn.in_proj_z.weight", "layers.21.linear_attn.out_proj.weight", "layers.21.mlp.down_proj.weight", "layers.21.mlp.gate_proj.weight", "layers.21.mlp.up_proj.weight", "layers.22.linear_attn.in_proj_a.weight", "layers.22.linear_attn.in_proj_b.weight", "layers.22.linear_attn.in_proj_qkv.weight", "layers.22.linear_attn.in_proj_z.weight", "layers.22.linear_attn.out_proj.weight", "layers.22.mlp.down_proj.weight", "layers.22.mlp.gate_proj.weight", "layers.22.mlp.up_proj.weight", "layers.23.mlp.down_proj.weight", "layers.23.mlp.gate_proj.weight", "layers.23.mlp.up_proj.weight", "layers.23.self_attn.k_proj.weight", "layers.23.self_attn.o_proj.weight", "layers.23.self_attn.q_proj.weight", "layers.23.self_attn.v_proj.weight", "layers.24.linear_attn.in_proj_a.weight", "layers.24.linear_attn.in_proj_b.weight", "layers.24.linear_attn.in_proj_qkv.weight", "layers.24.linear_attn.in_proj_z.weight", "layers.24.linear_attn.out_proj.weight", "layers.24.mlp.down_proj.weight", "layers.24.mlp.gate_proj.weight", "layers.24.mlp.up_proj.weight", "layers.25.linear_attn.in_proj_a.weight", "layers.25.linear_attn.in_proj_b.weight", "layers.25.linear_attn.in_proj_qkv.weight", "layers.25.linear_attn.in_proj_z.weight", "layers.25.linear_attn.out_proj.weight", "layers.25.mlp.down_proj.weight", "layers.25.mlp.gate_proj.weight", "layers.25.mlp.up_proj.weight", "layers.26.linear_attn.in_proj_a.weight", "layers.26.linear_attn.in_proj_b.weight", "layers.26.linear_attn.in_proj_qkv.weight", "layers.26.linear_attn.in_proj_z.weight", "layers.26.linear_attn.out_proj.weight", "layers.26.mlp.down_proj.weight", "layers.26.mlp.gate_proj.weight", "layers.26.mlp.up_proj.weight", "layers.27.mlp.down_proj.weight", "layers.27.mlp.gate_proj.weight", "layers.27.mlp.up_proj.weight", "layers.27.self_attn.k_proj.weight", "layers.27.self_attn.o_proj.weight", "layers.27.self_attn.q_proj.weight", "layers.27.self_attn.v_proj.weight", "layers.28.linear_attn.in_proj_a.weight", "layers.28.linear_attn.in_proj_b.weight", "layers.28.linear_attn.in_proj_qkv.weight", "layers.28.linear_attn.in_proj_z.weight", "layers.28.linear_attn.out_proj.weight", "layers.28.mlp.down_proj.weight", "layers.28.mlp.gate_proj.weight", "layers.28.mlp.up_proj.weight", "layers.29.linear_attn.in_proj_a.weight", "layers.29.linear_attn.in_proj_b.weight", "layers.29.linear_attn.in_proj_qkv.weight", "layers.29.linear_attn.in_proj_z.weight", "layers.29.linear_attn.out_proj.weight", "layers.29.mlp.down_proj.weight", "layers.29.mlp.gate_proj.weight", "layers.29.mlp.up_proj.weight", "layers.30.linear_attn.in_proj_a.weight", "layers.30.linear_attn.in_proj_b.weight", "layers.30.linear_attn.in_proj_qkv.weight", "layers.30.linear_attn.in_proj_z.weight", "layers.30.linear_attn.out_proj.weight", "layers.30.mlp.down_proj.weight", "layers.30.mlp.gate_proj.weight", "layers.30.mlp.up_proj.weight", "layers.31.mlp.down_proj.weight", "layers.31.mlp.gate_proj.weight", "layers.31.mlp.up_proj.weight", "layers.31.self_attn.k_proj.weight", "layers.31.self_attn.o_proj.weight", "layers.31.self_attn.q_proj.weight", "layers.31.self_attn.v_proj.weight" ] }, "modules_quant_config": {}, "modules_to_not_convert": [ ".context_embedder", "wte", ".txt_out", ".vid_out", "patch_embedding", "time_text_embed", ".proj_out", ".t_embedder", ".x_embedder", "norm", ".time_embed", ".final_layer", ".condition_embedder", ".y_embedder", "multi_modal_projector", "patch_emb", ".img_out", ".proj_in", ".txt_in", ".norm_out", "patch_embed", ".img_in", "lm_head", ".emb_in", ".vid_in", ".emb_out", "embed_tokens.weight", "layers.0.input_layernorm.weight", "layers.0.linear_attn.conv1d.weight", "layers.0.post_attention_layernorm.weight", "layers.1.input_layernorm.weight", "layers.1.linear_attn.conv1d.weight", "layers.1.post_attention_layernorm.weight", "layers.2.input_layernorm.weight", "layers.2.linear_attn.conv1d.weight", "layers.2.post_attention_layernorm.weight", "layers.3.input_layernorm.weight", "layers.3.post_attention_layernorm.weight", "layers.3.self_attn.k_norm.weight", "layers.3.self_attn.q_norm.weight", "layers.4.input_layernorm.weight", "layers.4.linear_attn.conv1d.weight", "layers.4.post_attention_layernorm.weight", "layers.5.input_layernorm.weight", "layers.5.linear_attn.conv1d.weight", "layers.5.post_attention_layernorm.weight", "layers.6.input_layernorm.weight", "layers.6.linear_attn.conv1d.weight", "layers.6.post_attention_layernorm.weight", "layers.7.input_layernorm.weight", "layers.7.post_attention_layernorm.weight", "layers.7.self_attn.k_norm.weight", "layers.7.self_attn.q_norm.weight", "layers.8.input_layernorm.weight", "layers.8.linear_attn.conv1d.weight", "layers.8.post_attention_layernorm.weight", "layers.9.input_layernorm.weight", "layers.9.linear_attn.conv1d.weight", "layers.9.post_attention_layernorm.weight", "layers.10.input_layernorm.weight", "layers.10.linear_attn.conv1d.weight", "layers.10.post_attention_layernorm.weight", "layers.11.input_layernorm.weight", "layers.11.post_attention_layernorm.weight", "layers.11.self_attn.k_norm.weight", "layers.11.self_attn.q_norm.weight", "layers.12.input_layernorm.weight", "layers.12.linear_attn.conv1d.weight", "layers.12.post_attention_layernorm.weight", "layers.13.input_layernorm.weight", "layers.13.linear_attn.conv1d.weight", "layers.13.post_attention_layernorm.weight", "layers.14.input_layernorm.weight", "layers.14.linear_attn.conv1d.weight", "layers.14.post_attention_layernorm.weight", "layers.15.input_layernorm.weight", "layers.15.post_attention_layernorm.weight", "layers.15.self_attn.k_norm.weight", "layers.15.self_attn.q_norm.weight", "layers.16.input_layernorm.weight", "layers.16.linear_attn.conv1d.weight", "layers.16.post_attention_layernorm.weight", "layers.17.input_layernorm.weight", "layers.17.linear_attn.conv1d.weight", "layers.17.post_attention_layernorm.weight", "layers.18.input_layernorm.weight", "layers.18.linear_attn.conv1d.weight", "layers.18.post_attention_layernorm.weight", "layers.19.input_layernorm.weight", "layers.19.post_attention_layernorm.weight", "layers.19.self_attn.k_norm.weight", "layers.19.self_attn.q_norm.weight", "layers.20.input_layernorm.weight", "layers.20.linear_attn.conv1d.weight", "layers.20.post_attention_layernorm.weight", "layers.21.input_layernorm.weight", "layers.21.linear_attn.conv1d.weight", "layers.21.post_attention_layernorm.weight", "layers.22.input_layernorm.weight", "layers.22.linear_attn.conv1d.weight", "layers.22.post_attention_layernorm.weight", "layers.23.input_layernorm.weight", "layers.23.post_attention_layernorm.weight", "layers.23.self_attn.k_norm.weight", "layers.23.self_attn.q_norm.weight", "layers.24.input_layernorm.weight", "layers.24.linear_attn.conv1d.weight", "layers.24.post_attention_layernorm.weight", "layers.25.input_layernorm.weight", "layers.25.linear_attn.conv1d.weight", "layers.25.post_attention_layernorm.weight", "layers.26.input_layernorm.weight", "layers.26.linear_attn.conv1d.weight", "layers.26.post_attention_layernorm.weight", "layers.27.input_layernorm.weight", "layers.27.post_attention_layernorm.weight", "layers.27.self_attn.k_norm.weight", "layers.27.self_attn.q_norm.weight", "layers.28.input_layernorm.weight", "layers.28.linear_attn.conv1d.weight", "layers.28.post_attention_layernorm.weight", "layers.29.input_layernorm.weight", "layers.29.linear_attn.conv1d.weight", "layers.29.post_attention_layernorm.weight", "layers.30.input_layernorm.weight", "layers.30.linear_attn.conv1d.weight", "layers.30.post_attention_layernorm.weight", "layers.31.input_layernorm.weight", "layers.31.post_attention_layernorm.weight", "layers.31.self_attn.k_norm.weight", "layers.31.self_attn.q_norm.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, "scale_dtype": null, "sdnq_version": "0.2.8", "svd_rank": 32, "svd_steps": 8, "use_codebook": false, "use_codebook_scale": false, "use_dynamic_quantization": true, "use_grad_ckpt": true, "use_hadamard": true, "use_quantized_matmul": false, "use_quantized_matmul_conv": false, "use_static_quantization": true, "use_stochastic_rounding": false, "use_svd": false, "weights_dtype": "uint4", "zero_point_dtype": null }, "rms_norm_eps": 1e-06, "rope_parameters": { "mrope_interleaved": true, "mrope_section": [ 11, 11, 10 ], "partial_rotary_factor": 0.25, "rope_theta": 10000000, "rope_type": "default" }, "tie_word_embeddings": false, "transformers_version": "5.13.0", "use_cache": true, "vocab_size": 248320 }