{ "component": "text_encoder", "method": "sdnq", "weights_dtype": "uint4", "use_svd": true, "svd_rank": 32, "use_quantized_matmul": false, "skip_modules": [ "lm_head", "visual" ], "quantized_modules": [ "model.language_model.layers.0.self_attn.q_proj", "model.language_model.layers.0.self_attn.k_proj", "model.language_model.layers.0.self_attn.v_proj", "model.language_model.layers.0.self_attn.o_proj", "model.language_model.layers.0.mlp.gate_proj", "model.language_model.layers.0.mlp.up_proj", "model.language_model.layers.0.mlp.down_proj", "model.language_model.layers.1.self_attn.q_proj", "model.language_model.layers.1.self_attn.k_proj", "model.language_model.layers.1.self_attn.v_proj", "model.language_model.layers.1.self_attn.o_proj", "model.language_model.layers.1.mlp.gate_proj", "model.language_model.layers.1.mlp.up_proj", "model.language_model.layers.1.mlp.down_proj", "model.language_model.layers.2.self_attn.q_proj", "model.language_model.layers.2.self_attn.k_proj", "model.language_model.layers.2.self_attn.v_proj", "model.language_model.layers.2.self_attn.o_proj", "model.language_model.layers.2.mlp.gate_proj", "model.language_model.layers.2.mlp.up_proj", "model.language_model.layers.2.mlp.down_proj", "model.language_model.layers.3.self_attn.q_proj", "model.language_model.layers.3.self_attn.k_proj", "model.language_model.layers.3.self_attn.v_proj", "model.language_model.layers.3.self_attn.o_proj", "model.language_model.layers.3.mlp.gate_proj", "model.language_model.layers.3.mlp.up_proj", "model.language_model.layers.3.mlp.down_proj", "model.language_model.layers.4.self_attn.q_proj", "model.language_model.layers.4.self_attn.k_proj", "model.language_model.layers.4.self_attn.v_proj", "model.language_model.layers.4.self_attn.o_proj", "model.language_model.layers.4.mlp.gate_proj", "model.language_model.layers.4.mlp.up_proj", "model.language_model.layers.4.mlp.down_proj", "model.language_model.layers.5.self_attn.q_proj", "model.language_model.layers.5.self_attn.k_proj", "model.language_model.layers.5.self_attn.v_proj", "model.language_model.layers.5.self_attn.o_proj", "model.language_model.layers.5.mlp.gate_proj", "model.language_model.layers.5.mlp.up_proj", "model.language_model.layers.5.mlp.down_proj", "model.language_model.layers.6.self_attn.q_proj", "model.language_model.layers.6.self_attn.k_proj", "model.language_model.layers.6.self_attn.v_proj", "model.language_model.layers.6.self_attn.o_proj", "model.language_model.layers.6.mlp.gate_proj", "model.language_model.layers.6.mlp.up_proj", "model.language_model.layers.6.mlp.down_proj", "model.language_model.layers.7.self_attn.q_proj", "model.language_model.layers.7.self_attn.k_proj", "model.language_model.layers.7.self_attn.v_proj", "model.language_model.layers.7.self_attn.o_proj", "model.language_model.layers.7.mlp.gate_proj", "model.language_model.layers.7.mlp.up_proj", "model.language_model.layers.7.mlp.down_proj", "model.language_model.layers.8.self_attn.q_proj", "model.language_model.layers.8.self_attn.k_proj", "model.language_model.layers.8.self_attn.v_proj", "model.language_model.layers.8.self_attn.o_proj", "model.language_model.layers.8.mlp.gate_proj", "model.language_model.layers.8.mlp.up_proj", "model.language_model.layers.8.mlp.down_proj", "model.language_model.layers.9.self_attn.q_proj", "model.language_model.layers.9.self_attn.k_proj", "model.language_model.layers.9.self_attn.v_proj", "model.language_model.layers.9.self_attn.o_proj", "model.language_model.layers.9.mlp.gate_proj", "model.language_model.layers.9.mlp.up_proj", "model.language_model.layers.9.mlp.down_proj", "model.language_model.layers.10.self_attn.q_proj", "model.language_model.layers.10.self_attn.k_proj", "model.language_model.layers.10.self_attn.v_proj", "model.language_model.layers.10.self_attn.o_proj", "model.language_model.layers.10.mlp.gate_proj", "model.language_model.layers.10.mlp.up_proj", "model.language_model.layers.10.mlp.down_proj", "model.language_model.layers.11.self_attn.q_proj", "model.language_model.layers.11.self_attn.k_proj", "model.language_model.layers.11.self_attn.v_proj", "model.language_model.layers.11.self_attn.o_proj", "model.language_model.layers.11.mlp.gate_proj", "model.language_model.layers.11.mlp.up_proj", "model.language_model.layers.11.mlp.down_proj", "model.language_model.layers.12.self_attn.q_proj", "model.language_model.layers.12.self_attn.k_proj", "model.language_model.layers.12.self_attn.v_proj", "model.language_model.layers.12.self_attn.o_proj", "model.language_model.layers.12.mlp.gate_proj", "model.language_model.layers.12.mlp.up_proj", "model.language_model.layers.12.mlp.down_proj", "model.language_model.layers.13.self_attn.q_proj", "model.language_model.layers.13.self_attn.k_proj", "model.language_model.layers.13.self_attn.v_proj", "model.language_model.layers.13.self_attn.o_proj", "model.language_model.layers.13.mlp.gate_proj", "model.language_model.layers.13.mlp.up_proj", "model.language_model.layers.13.mlp.down_proj", "model.language_model.layers.14.self_attn.q_proj", "model.language_model.layers.14.self_attn.k_proj", "model.language_model.layers.14.self_attn.v_proj", "model.language_model.layers.14.self_attn.o_proj", "model.language_model.layers.14.mlp.gate_proj", "model.language_model.layers.14.mlp.up_proj", "model.language_model.layers.14.mlp.down_proj", "model.language_model.layers.15.self_attn.q_proj", "model.language_model.layers.15.self_attn.k_proj", "model.language_model.layers.15.self_attn.v_proj", "model.language_model.layers.15.self_attn.o_proj", "model.language_model.layers.15.mlp.gate_proj", "model.language_model.layers.15.mlp.up_proj", "model.language_model.layers.15.mlp.down_proj", "model.language_model.layers.16.self_attn.q_proj", "model.language_model.layers.16.self_attn.k_proj", "model.language_model.layers.16.self_attn.v_proj", "model.language_model.layers.16.self_attn.o_proj", "model.language_model.layers.16.mlp.gate_proj", "model.language_model.layers.16.mlp.up_proj", "model.language_model.layers.16.mlp.down_proj", "model.language_model.layers.17.self_attn.q_proj", "model.language_model.layers.17.self_attn.k_proj", "model.language_model.layers.17.self_attn.v_proj", "model.language_model.layers.17.self_attn.o_proj", "model.language_model.layers.17.mlp.gate_proj", "model.language_model.layers.17.mlp.up_proj", "model.language_model.layers.17.mlp.down_proj", "model.language_model.layers.18.self_attn.q_proj", "model.language_model.layers.18.self_attn.k_proj", "model.language_model.layers.18.self_attn.v_proj", "model.language_model.layers.18.self_attn.o_proj", "model.language_model.layers.18.mlp.gate_proj", "model.language_model.layers.18.mlp.up_proj", "model.language_model.layers.18.mlp.down_proj", "model.language_model.layers.19.self_attn.q_proj", "model.language_model.layers.19.self_attn.k_proj", "model.language_model.layers.19.self_attn.v_proj", "model.language_model.layers.19.self_attn.o_proj", "model.language_model.layers.19.mlp.gate_proj", "model.language_model.layers.19.mlp.up_proj", "model.language_model.layers.19.mlp.down_proj", "model.language_model.layers.20.self_attn.q_proj", "model.language_model.layers.20.self_attn.k_proj", "model.language_model.layers.20.self_attn.v_proj", "model.language_model.layers.20.self_attn.o_proj", "model.language_model.layers.20.mlp.gate_proj", "model.language_model.layers.20.mlp.up_proj", "model.language_model.layers.20.mlp.down_proj", "model.language_model.layers.21.self_attn.q_proj", "model.language_model.layers.21.self_attn.k_proj", "model.language_model.layers.21.self_attn.v_proj", "model.language_model.layers.21.self_attn.o_proj", "model.language_model.layers.21.mlp.gate_proj", "model.language_model.layers.21.mlp.up_proj", "model.language_model.layers.21.mlp.down_proj", "model.language_model.layers.22.self_attn.q_proj", "model.language_model.layers.22.self_attn.k_proj", "model.language_model.layers.22.self_attn.v_proj", "model.language_model.layers.22.self_attn.o_proj", "model.language_model.layers.22.mlp.gate_proj", "model.language_model.layers.22.mlp.up_proj", "model.language_model.layers.22.mlp.down_proj", "model.language_model.layers.23.self_attn.q_proj", "model.language_model.layers.23.self_attn.k_proj", "model.language_model.layers.23.self_attn.v_proj", "model.language_model.layers.23.self_attn.o_proj", "model.language_model.layers.23.mlp.gate_proj", "model.language_model.layers.23.mlp.up_proj", "model.language_model.layers.23.mlp.down_proj", "model.language_model.layers.24.self_attn.q_proj", "model.language_model.layers.24.self_attn.k_proj", "model.language_model.layers.24.self_attn.v_proj", "model.language_model.layers.24.self_attn.o_proj", "model.language_model.layers.24.mlp.gate_proj", "model.language_model.layers.24.mlp.up_proj", "model.language_model.layers.24.mlp.down_proj", "model.language_model.layers.25.self_attn.q_proj", "model.language_model.layers.25.self_attn.k_proj", "model.language_model.layers.25.self_attn.v_proj", "model.language_model.layers.25.self_attn.o_proj", "model.language_model.layers.25.mlp.gate_proj", "model.language_model.layers.25.mlp.up_proj", "model.language_model.layers.25.mlp.down_proj", "model.language_model.layers.26.self_attn.q_proj", "model.language_model.layers.26.self_attn.k_proj", "model.language_model.layers.26.self_attn.v_proj", "model.language_model.layers.26.self_attn.o_proj", "model.language_model.layers.26.mlp.gate_proj", "model.language_model.layers.26.mlp.up_proj", "model.language_model.layers.26.mlp.down_proj", "model.language_model.layers.27.self_attn.q_proj", "model.language_model.layers.27.self_attn.k_proj", "model.language_model.layers.27.self_attn.v_proj", "model.language_model.layers.27.self_attn.o_proj", "model.language_model.layers.27.mlp.gate_proj", "model.language_model.layers.27.mlp.up_proj", "model.language_model.layers.27.mlp.down_proj", "model.language_model.layers.28.self_attn.q_proj", "model.language_model.layers.28.self_attn.k_proj", "model.language_model.layers.28.self_attn.v_proj", "model.language_model.layers.28.self_attn.o_proj", "model.language_model.layers.28.mlp.gate_proj", "model.language_model.layers.28.mlp.up_proj", "model.language_model.layers.28.mlp.down_proj", "model.language_model.layers.29.self_attn.q_proj", "model.language_model.layers.29.self_attn.k_proj", "model.language_model.layers.29.self_attn.v_proj", "model.language_model.layers.29.self_attn.o_proj", "model.language_model.layers.29.mlp.gate_proj", "model.language_model.layers.29.mlp.up_proj", "model.language_model.layers.29.mlp.down_proj", "model.language_model.layers.30.self_attn.q_proj", "model.language_model.layers.30.self_attn.k_proj", "model.language_model.layers.30.self_attn.v_proj", "model.language_model.layers.30.self_attn.o_proj", "model.language_model.layers.30.mlp.gate_proj", "model.language_model.layers.30.mlp.up_proj", "model.language_model.layers.30.mlp.down_proj", "model.language_model.layers.31.self_attn.q_proj", "model.language_model.layers.31.self_attn.k_proj", "model.language_model.layers.31.self_attn.v_proj", "model.language_model.layers.31.self_attn.o_proj", "model.language_model.layers.31.mlp.gate_proj", "model.language_model.layers.31.mlp.up_proj", "model.language_model.layers.31.mlp.down_proj", "model.language_model.layers.32.self_attn.q_proj", "model.language_model.layers.32.self_attn.k_proj", "model.language_model.layers.32.self_attn.v_proj", "model.language_model.layers.32.self_attn.o_proj", "model.language_model.layers.32.mlp.gate_proj", "model.language_model.layers.32.mlp.up_proj", "model.language_model.layers.32.mlp.down_proj", "model.language_model.layers.33.self_attn.q_proj", "model.language_model.layers.33.self_attn.k_proj", "model.language_model.layers.33.self_attn.v_proj", "model.language_model.layers.33.self_attn.o_proj", "model.language_model.layers.33.mlp.gate_proj", "model.language_model.layers.33.mlp.up_proj", "model.language_model.layers.33.mlp.down_proj", "model.language_model.layers.34.self_attn.q_proj", "model.language_model.layers.34.self_attn.k_proj", "model.language_model.layers.34.self_attn.v_proj", "model.language_model.layers.34.self_attn.o_proj", "model.language_model.layers.34.mlp.gate_proj", "model.language_model.layers.34.mlp.up_proj", "model.language_model.layers.34.mlp.down_proj", "model.language_model.layers.35.self_attn.q_proj", "model.language_model.layers.35.self_attn.k_proj", "model.language_model.layers.35.self_attn.v_proj", "model.language_model.layers.35.self_attn.o_proj", "model.language_model.layers.35.mlp.gate_proj", "model.language_model.layers.35.mlp.up_proj", "model.language_model.layers.35.mlp.down_proj" ], "module_types": { "Qwen3VLForConditionalGeneration": 1, "Qwen3VLModel": 1, "Qwen3VLVisionModel": 1, "Qwen3VLVisionPatchEmbed": 1, "Conv3d": 1, "Embedding": 2, "Qwen3VLVisionRotaryEmbedding": 1, "ModuleList": 3, "Qwen3VLVisionBlock": 27, "LayerNorm": 58, "Qwen3VLVisionAttention": 27, "Linear": 117, "Qwen3VLVisionMLP": 27, "GELUTanh": 27, "Qwen3VLVisionPatchMerger": 4, "GELU": 4, "Qwen3VLTextModel": 1, "Qwen3VLTextDecoderLayer": 36, "Qwen3VLTextAttention": 36, "SDNQLinear": 252, "Qwen3VLTextRMSNorm": 145, "Qwen3VLTextMLP": 36, "SiLUActivation": 36, "Qwen3VLTextRotaryEmbedding": 1 }, "parameter_dtypes": { "torch.bfloat16": 1908650224, "torch.uint8": 3472883712, "torch.float32": 108527616 }, "saved_quantization_config": { "add_skip_keys": true, "codebook_steps": 24, "dequantize_fp32": true, "dynamic_loss_threshold": null, "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": {}, "modules_quant_config": {}, "modules_to_not_convert": [ "multi_modal_projector", ".x_embedder", ".proj_in", "patch_embedding", ".t_embedder", ".norm_out", ".img_out", "wte", ".txt_out", ".vid_in", ".time_embed", "model.language_model.embed_tokens.weight", ".vid_out", ".context_embedder", ".emb_out", "lm_head", ".y_embedder", ".emb_in", ".final_layer", "time_text_embed", ".img_in", "patch_emb", ".proj_out", "visual", ".txt_in", ".condition_embedder", "lm_head.weight", "patch_embed", "model.language_model.layers.0.input_layernorm.weight", "model.language_model.layers.0.post_attention_layernorm.weight", "model.language_model.layers.0.self_attn.k_norm.weight", "model.language_model.layers.0.self_attn.q_norm.weight", "model.language_model.layers.1.input_layernorm.weight", "model.language_model.layers.1.post_attention_layernorm.weight", "model.language_model.layers.1.self_attn.k_norm.weight", "model.language_model.layers.1.self_attn.q_norm.weight", "model.language_model.layers.2.input_layernorm.weight", "model.language_model.layers.2.post_attention_layernorm.weight", "model.language_model.layers.2.self_attn.k_norm.weight", "model.language_model.layers.2.self_attn.q_norm.weight", "model.language_model.layers.3.input_layernorm.weight", "model.language_model.layers.3.post_attention_layernorm.weight", "model.language_model.layers.3.self_attn.k_norm.weight", "model.language_model.layers.3.self_attn.q_norm.weight", "model.language_model.layers.4.input_layernorm.weight", "model.language_model.layers.4.post_attention_layernorm.weight", "model.language_model.layers.4.self_attn.k_norm.weight", "model.language_model.layers.4.self_attn.q_norm.weight", "model.language_model.layers.5.input_layernorm.weight", "model.language_model.layers.5.post_attention_layernorm.weight", "model.language_model.layers.5.self_attn.k_norm.weight", "model.language_model.layers.5.self_attn.q_norm.weight", "model.language_model.layers.6.input_layernorm.weight", "model.language_model.layers.6.post_attention_layernorm.weight", "model.language_model.layers.6.self_attn.k_norm.weight", "model.language_model.layers.6.self_attn.q_norm.weight", "model.language_model.layers.7.input_layernorm.weight", "model.language_model.layers.7.post_attention_layernorm.weight", "model.language_model.layers.7.self_attn.k_norm.weight", "model.language_model.layers.7.self_attn.q_norm.weight", "model.language_model.layers.8.input_layernorm.weight", "model.language_model.layers.8.post_attention_layernorm.weight", "model.language_model.layers.8.self_attn.k_norm.weight", "model.language_model.layers.8.self_attn.q_norm.weight", "model.language_model.layers.9.input_layernorm.weight", "model.language_model.layers.9.post_attention_layernorm.weight", "model.language_model.layers.9.self_attn.k_norm.weight", "model.language_model.layers.9.self_attn.q_norm.weight", "model.language_model.layers.10.input_layernorm.weight", "model.language_model.layers.10.post_attention_layernorm.weight", "model.language_model.layers.10.self_attn.k_norm.weight", "model.language_model.layers.10.self_attn.q_norm.weight", "model.language_model.layers.11.input_layernorm.weight", "model.language_model.layers.11.post_attention_layernorm.weight", "model.language_model.layers.11.self_attn.k_norm.weight", "model.language_model.layers.11.self_attn.q_norm.weight", "model.language_model.layers.12.input_layernorm.weight", "model.language_model.layers.12.post_attention_layernorm.weight", "model.language_model.layers.12.self_attn.k_norm.weight", "model.language_model.layers.12.self_attn.q_norm.weight", "model.language_model.layers.13.input_layernorm.weight", "model.language_model.layers.13.post_attention_layernorm.weight", "model.language_model.layers.13.self_attn.k_norm.weight", "model.language_model.layers.13.self_attn.q_norm.weight", "model.language_model.layers.14.input_layernorm.weight", "model.language_model.layers.14.post_attention_layernorm.weight", "model.language_model.layers.14.self_attn.k_norm.weight", "model.language_model.layers.14.self_attn.q_norm.weight", "model.language_model.layers.15.input_layernorm.weight", "model.language_model.layers.15.post_attention_layernorm.weight", "model.language_model.layers.15.self_attn.k_norm.weight", "model.language_model.layers.15.self_attn.q_norm.weight", "model.language_model.layers.16.input_layernorm.weight", "model.language_model.layers.16.post_attention_layernorm.weight", "model.language_model.layers.16.self_attn.k_norm.weight", "model.language_model.layers.16.self_attn.q_norm.weight", "model.language_model.layers.17.input_layernorm.weight", "model.language_model.layers.17.post_attention_layernorm.weight", "model.language_model.layers.17.self_attn.k_norm.weight", "model.language_model.layers.17.self_attn.q_norm.weight", "model.language_model.layers.18.input_layernorm.weight", "model.language_model.layers.18.post_attention_layernorm.weight", "model.language_model.layers.18.self_attn.k_norm.weight", "model.language_model.layers.18.self_attn.q_norm.weight", "model.language_model.layers.19.input_layernorm.weight", "model.language_model.layers.19.post_attention_layernorm.weight", "model.language_model.layers.19.self_attn.k_norm.weight", "model.language_model.layers.19.self_attn.q_norm.weight", "model.language_model.layers.20.input_layernorm.weight", "model.language_model.layers.20.post_attention_layernorm.weight", "model.language_model.layers.20.self_attn.k_norm.weight", "model.language_model.layers.20.self_attn.q_norm.weight", "model.language_model.layers.21.input_layernorm.weight", "model.language_model.layers.21.post_attention_layernorm.weight", "model.language_model.layers.21.self_attn.k_norm.weight", "model.language_model.layers.21.self_attn.q_norm.weight", "model.language_model.layers.22.input_layernorm.weight", "model.language_model.layers.22.post_attention_layernorm.weight", "model.language_model.layers.22.self_attn.k_norm.weight", "model.language_model.layers.22.self_attn.q_norm.weight", "model.language_model.layers.23.input_layernorm.weight", "model.language_model.layers.23.post_attention_layernorm.weight", "model.language_model.layers.23.self_attn.k_norm.weight", "model.language_model.layers.23.self_attn.q_norm.weight", "model.language_model.layers.24.input_layernorm.weight", "model.language_model.layers.24.post_attention_layernorm.weight", "model.language_model.layers.24.self_attn.k_norm.weight", "model.language_model.layers.24.self_attn.q_norm.weight", "model.language_model.layers.25.input_layernorm.weight", "model.language_model.layers.25.post_attention_layernorm.weight", "model.language_model.layers.25.self_attn.k_norm.weight", "model.language_model.layers.25.self_attn.q_norm.weight", "model.language_model.layers.26.input_layernorm.weight", "model.language_model.layers.26.post_attention_layernorm.weight", "model.language_model.layers.26.self_attn.k_norm.weight", "model.language_model.layers.26.self_attn.q_norm.weight", "model.language_model.layers.27.input_layernorm.weight", "model.language_model.layers.27.post_attention_layernorm.weight", "model.language_model.layers.27.self_attn.k_norm.weight", "model.language_model.layers.27.self_attn.q_norm.weight", "model.language_model.layers.28.input_layernorm.weight", "model.language_model.layers.28.post_attention_layernorm.weight", "model.language_model.layers.28.self_attn.k_norm.weight", "model.language_model.layers.28.self_attn.q_norm.weight", "model.language_model.layers.29.input_layernorm.weight", "model.language_model.layers.29.post_attention_layernorm.weight", "model.language_model.layers.29.self_attn.k_norm.weight", "model.language_model.layers.29.self_attn.q_norm.weight", "model.language_model.layers.30.input_layernorm.weight", "model.language_model.layers.30.post_attention_layernorm.weight", "model.language_model.layers.30.self_attn.k_norm.weight", "model.language_model.layers.30.self_attn.q_norm.weight", "model.language_model.layers.31.input_layernorm.weight", "model.language_model.layers.31.post_attention_layernorm.weight", "model.language_model.layers.31.self_attn.k_norm.weight", "model.language_model.layers.31.self_attn.q_norm.weight", "model.language_model.layers.32.input_layernorm.weight", "model.language_model.layers.32.post_attention_layernorm.weight", "model.language_model.layers.32.self_attn.k_norm.weight", "model.language_model.layers.32.self_attn.q_norm.weight", "model.language_model.layers.33.input_layernorm.weight", "model.language_model.layers.33.post_attention_layernorm.weight", "model.language_model.layers.33.self_attn.k_norm.weight", "model.language_model.layers.33.self_attn.q_norm.weight", "model.language_model.layers.34.input_layernorm.weight", "model.language_model.layers.34.post_attention_layernorm.weight", "model.language_model.layers.34.self_attn.k_norm.weight", "model.language_model.layers.34.self_attn.q_norm.weight", "model.language_model.layers.35.input_layernorm.weight", "model.language_model.layers.35.post_attention_layernorm.weight", "model.language_model.layers.35.self_attn.k_norm.weight", "model.language_model.layers.35.self_attn.q_norm.weight", "model.language_model.norm.weight" ], "modules_to_not_use_matmul": [], "non_blocking": false, "quant_conv": false, "quant_embedding": false, "quant_method": "sdnq", "quantization_device": "cuda:0", "quantized_matmul_dtype": null, "return_device": "cpu", "sdnq_version": "0.2.7", "svd_rank": 32, "svd_steps": 8, "use_codebook": false, "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": true, "weights_dtype": "uint4" } }