Image21-INT4 / transformer-quantization.json
ixim's picture
Release verified Image21-INT4 conversion
9116984 verified
Raw History Blame Contribute Delete
15.6 kB
{
"component": "transformer",
"method": "sdnq",
"weights_dtype": "uint4",
"use_svd": true,
"svd_rank": 32,
"use_quantized_matmul": false,
"skip_modules": [
"proj_out",
"img_in",
"txt_in",
"time_text_embed",
"modulation",
"norm_out"
],
"quantized_modules": [
"transformer_blocks.0.attn.to_q",
"transformer_blocks.0.attn.to_k",
"transformer_blocks.0.attn.to_v",
"transformer_blocks.0.attn.to_out.0",
"transformer_blocks.0.img_mlp.proj",
"transformer_blocks.0.img_mlp.out",
"transformer_blocks.0.img_mlp.gate_layer",
"transformer_blocks.1.attn.to_q",
"transformer_blocks.1.attn.to_k",
"transformer_blocks.1.attn.to_v",
"transformer_blocks.1.attn.to_out.0",
"transformer_blocks.1.img_mlp.proj",
"transformer_blocks.1.img_mlp.out",
"transformer_blocks.1.img_mlp.gate_layer",
"transformer_blocks.2.attn.to_q",
"transformer_blocks.2.attn.to_k",
"transformer_blocks.2.attn.to_v",
"transformer_blocks.2.attn.to_out.0",
"transformer_blocks.2.img_mlp.proj",
"transformer_blocks.2.img_mlp.out",
"transformer_blocks.2.img_mlp.gate_layer",
"transformer_blocks.3.attn.to_q",
"transformer_blocks.3.attn.to_k",
"transformer_blocks.3.attn.to_v",
"transformer_blocks.3.attn.to_out.0",
"transformer_blocks.3.img_mlp.proj",
"transformer_blocks.3.img_mlp.out",
"transformer_blocks.3.img_mlp.gate_layer",
"transformer_blocks.4.attn.to_q",
"transformer_blocks.4.attn.to_k",
"transformer_blocks.4.attn.to_v",
"transformer_blocks.4.attn.to_out.0",
"transformer_blocks.4.img_mlp.proj",
"transformer_blocks.4.img_mlp.out",
"transformer_blocks.4.img_mlp.gate_layer",
"transformer_blocks.5.attn.to_q",
"transformer_blocks.5.attn.to_k",
"transformer_blocks.5.attn.to_v",
"transformer_blocks.5.attn.to_out.0",
"transformer_blocks.5.img_mlp.proj",
"transformer_blocks.5.img_mlp.out",
"transformer_blocks.5.img_mlp.gate_layer",
"transformer_blocks.6.attn.to_q",
"transformer_blocks.6.attn.to_k",
"transformer_blocks.6.attn.to_v",
"transformer_blocks.6.attn.to_out.0",
"transformer_blocks.6.img_mlp.proj",
"transformer_blocks.6.img_mlp.out",
"transformer_blocks.6.img_mlp.gate_layer",
"transformer_blocks.7.attn.to_q",
"transformer_blocks.7.attn.to_k",
"transformer_blocks.7.attn.to_v",
"transformer_blocks.7.attn.to_out.0",
"transformer_blocks.7.img_mlp.proj",
"transformer_blocks.7.img_mlp.out",
"transformer_blocks.7.img_mlp.gate_layer",
"transformer_blocks.8.attn.to_q",
"transformer_blocks.8.attn.to_k",
"transformer_blocks.8.attn.to_v",
"transformer_blocks.8.attn.to_out.0",
"transformer_blocks.8.img_mlp.proj",
"transformer_blocks.8.img_mlp.out",
"transformer_blocks.8.img_mlp.gate_layer",
"transformer_blocks.9.attn.to_q",
"transformer_blocks.9.attn.to_k",
"transformer_blocks.9.attn.to_v",
"transformer_blocks.9.attn.to_out.0",
"transformer_blocks.9.img_mlp.proj",
"transformer_blocks.9.img_mlp.out",
"transformer_blocks.9.img_mlp.gate_layer",
"transformer_blocks.10.attn.to_q",
"transformer_blocks.10.attn.to_k",
"transformer_blocks.10.attn.to_v",
"transformer_blocks.10.attn.to_out.0",
"transformer_blocks.10.img_mlp.proj",
"transformer_blocks.10.img_mlp.out",
"transformer_blocks.10.img_mlp.gate_layer",
"transformer_blocks.11.attn.to_q",
"transformer_blocks.11.attn.to_k",
"transformer_blocks.11.attn.to_v",
"transformer_blocks.11.attn.to_out.0",
"transformer_blocks.11.img_mlp.proj",
"transformer_blocks.11.img_mlp.out",
"transformer_blocks.11.img_mlp.gate_layer",
"transformer_blocks.12.attn.to_q",
"transformer_blocks.12.attn.to_k",
"transformer_blocks.12.attn.to_v",
"transformer_blocks.12.attn.to_out.0",
"transformer_blocks.12.img_mlp.proj",
"transformer_blocks.12.img_mlp.out",
"transformer_blocks.12.img_mlp.gate_layer",
"transformer_blocks.13.attn.to_q",
"transformer_blocks.13.attn.to_k",
"transformer_blocks.13.attn.to_v",
"transformer_blocks.13.attn.to_out.0",
"transformer_blocks.13.img_mlp.proj",
"transformer_blocks.13.img_mlp.out",
"transformer_blocks.13.img_mlp.gate_layer",
"transformer_blocks.14.attn.to_q",
"transformer_blocks.14.attn.to_k",
"transformer_blocks.14.attn.to_v",
"transformer_blocks.14.attn.to_out.0",
"transformer_blocks.14.img_mlp.proj",
"transformer_blocks.14.img_mlp.out",
"transformer_blocks.14.img_mlp.gate_layer",
"transformer_blocks.15.attn.to_q",
"transformer_blocks.15.attn.to_k",
"transformer_blocks.15.attn.to_v",
"transformer_blocks.15.attn.to_out.0",
"transformer_blocks.15.img_mlp.proj",
"transformer_blocks.15.img_mlp.out",
"transformer_blocks.15.img_mlp.gate_layer",
"transformer_blocks.16.attn.to_q",
"transformer_blocks.16.attn.to_k",
"transformer_blocks.16.attn.to_v",
"transformer_blocks.16.attn.to_out.0",
"transformer_blocks.16.img_mlp.proj",
"transformer_blocks.16.img_mlp.out",
"transformer_blocks.16.img_mlp.gate_layer",
"transformer_blocks.17.attn.to_q",
"transformer_blocks.17.attn.to_k",
"transformer_blocks.17.attn.to_v",
"transformer_blocks.17.attn.to_out.0",
"transformer_blocks.17.img_mlp.proj",
"transformer_blocks.17.img_mlp.out",
"transformer_blocks.17.img_mlp.gate_layer",
"transformer_blocks.18.attn.to_q",
"transformer_blocks.18.attn.to_k",
"transformer_blocks.18.attn.to_v",
"transformer_blocks.18.attn.to_out.0",
"transformer_blocks.18.img_mlp.proj",
"transformer_blocks.18.img_mlp.out",
"transformer_blocks.18.img_mlp.gate_layer",
"transformer_blocks.19.attn.to_q",
"transformer_blocks.19.attn.to_k",
"transformer_blocks.19.attn.to_v",
"transformer_blocks.19.attn.to_out.0",
"transformer_blocks.19.img_mlp.proj",
"transformer_blocks.19.img_mlp.out",
"transformer_blocks.19.img_mlp.gate_layer",
"transformer_blocks.20.attn.to_q",
"transformer_blocks.20.attn.to_k",
"transformer_blocks.20.attn.to_v",
"transformer_blocks.20.attn.to_out.0",
"transformer_blocks.20.img_mlp.proj",
"transformer_blocks.20.img_mlp.out",
"transformer_blocks.20.img_mlp.gate_layer",
"transformer_blocks.21.attn.to_q",
"transformer_blocks.21.attn.to_k",
"transformer_blocks.21.attn.to_v",
"transformer_blocks.21.attn.to_out.0",
"transformer_blocks.21.img_mlp.proj",
"transformer_blocks.21.img_mlp.out",
"transformer_blocks.21.img_mlp.gate_layer",
"transformer_blocks.22.attn.to_q",
"transformer_blocks.22.attn.to_k",
"transformer_blocks.22.attn.to_v",
"transformer_blocks.22.attn.to_out.0",
"transformer_blocks.22.img_mlp.proj",
"transformer_blocks.22.img_mlp.out",
"transformer_blocks.22.img_mlp.gate_layer",
"transformer_blocks.23.attn.to_q",
"transformer_blocks.23.attn.to_k",
"transformer_blocks.23.attn.to_v",
"transformer_blocks.23.attn.to_out.0",
"transformer_blocks.23.img_mlp.proj",
"transformer_blocks.23.img_mlp.out",
"transformer_blocks.23.img_mlp.gate_layer",
"transformer_blocks.24.attn.to_q",
"transformer_blocks.24.attn.to_k",
"transformer_blocks.24.attn.to_v",
"transformer_blocks.24.attn.to_out.0",
"transformer_blocks.24.img_mlp.proj",
"transformer_blocks.24.img_mlp.out",
"transformer_blocks.24.img_mlp.gate_layer",
"transformer_blocks.25.attn.to_q",
"transformer_blocks.25.attn.to_k",
"transformer_blocks.25.attn.to_v",
"transformer_blocks.25.attn.to_out.0",
"transformer_blocks.25.img_mlp.proj",
"transformer_blocks.25.img_mlp.out",
"transformer_blocks.25.img_mlp.gate_layer",
"transformer_blocks.26.attn.to_q",
"transformer_blocks.26.attn.to_k",
"transformer_blocks.26.attn.to_v",
"transformer_blocks.26.attn.to_out.0",
"transformer_blocks.26.img_mlp.proj",
"transformer_blocks.26.img_mlp.out",
"transformer_blocks.26.img_mlp.gate_layer",
"transformer_blocks.27.attn.to_q",
"transformer_blocks.27.attn.to_k",
"transformer_blocks.27.attn.to_v",
"transformer_blocks.27.attn.to_out.0",
"transformer_blocks.27.img_mlp.proj",
"transformer_blocks.27.img_mlp.out",
"transformer_blocks.27.img_mlp.gate_layer",
"transformer_blocks.28.attn.to_q",
"transformer_blocks.28.attn.to_k",
"transformer_blocks.28.attn.to_v",
"transformer_blocks.28.attn.to_out.0",
"transformer_blocks.28.img_mlp.proj",
"transformer_blocks.28.img_mlp.out",
"transformer_blocks.28.img_mlp.gate_layer",
"transformer_blocks.29.attn.to_q",
"transformer_blocks.29.attn.to_k",
"transformer_blocks.29.attn.to_v",
"transformer_blocks.29.attn.to_out.0",
"transformer_blocks.29.img_mlp.proj",
"transformer_blocks.29.img_mlp.out",
"transformer_blocks.29.img_mlp.gate_layer",
"transformer_blocks.30.attn.to_q",
"transformer_blocks.30.attn.to_k",
"transformer_blocks.30.attn.to_v",
"transformer_blocks.30.attn.to_out.0",
"transformer_blocks.30.img_mlp.proj",
"transformer_blocks.30.img_mlp.out",
"transformer_blocks.30.img_mlp.gate_layer",
"transformer_blocks.31.attn.to_q",
"transformer_blocks.31.attn.to_k",
"transformer_blocks.31.attn.to_v",
"transformer_blocks.31.attn.to_out.0",
"transformer_blocks.31.img_mlp.proj",
"transformer_blocks.31.img_mlp.out",
"transformer_blocks.31.img_mlp.gate_layer"
],
"module_types": {
"QwenImage21Transformer2DModel": 1,
"QwenImage21Rope": 1,
"QwenImage21TimestepProjEmbeddings": 1,
"QwenImage21TemporalTimesteps": 1,
"TimestepEmbedding": 1,
"Linear": 8,
"SiLU": 35,
"QwenImage21TextProjection": 1,
"QwenImage21ZeroCenterRMSNorm": 1,
"GELU": 1,
"Sequential": 1,
"ModuleList": 33,
"QwenImage21TransformerBlock": 32,
"LayerNorm": 65,
"QwenImage21Attention": 32,
"SDNQLinear": 224,
"Dropout": 32,
"RMSNorm": 64,
"QwenImage21SwiGLUFeedForward": 32,
"QwenImage21AdaLayerNormContinuous": 1
},
"parameter_dtypes": {
"torch.bfloat16": 219688960,
"torch.uint8": 3489660928,
"torch.float32": 109051904
},
"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",
"proj_out",
".vid_out",
".context_embedder",
"pos_embed",
"norm_out",
".emb_out",
"lm_head",
"norm",
".y_embedder",
".emb_in",
"img_in",
".final_layer",
"time_text_embed",
".img_in",
"patch_emb",
".proj_out",
".txt_in",
"txt_in",
".condition_embedder",
"patch_embed",
"modulation",
"transformer_blocks.0.attn.norm_k.weight",
"transformer_blocks.0.attn.norm_q.weight",
"transformer_blocks.1.attn.norm_k.weight",
"transformer_blocks.1.attn.norm_q.weight",
"transformer_blocks.10.attn.norm_k.weight",
"transformer_blocks.10.attn.norm_q.weight",
"transformer_blocks.11.attn.norm_k.weight",
"transformer_blocks.11.attn.norm_q.weight",
"transformer_blocks.12.attn.norm_k.weight",
"transformer_blocks.12.attn.norm_q.weight",
"transformer_blocks.13.attn.norm_k.weight",
"transformer_blocks.13.attn.norm_q.weight",
"transformer_blocks.14.attn.norm_k.weight",
"transformer_blocks.14.attn.norm_q.weight",
"transformer_blocks.15.attn.norm_k.weight",
"transformer_blocks.15.attn.norm_q.weight",
"transformer_blocks.16.attn.norm_k.weight",
"transformer_blocks.16.attn.norm_q.weight",
"transformer_blocks.17.attn.norm_k.weight",
"transformer_blocks.17.attn.norm_q.weight",
"transformer_blocks.18.attn.norm_k.weight",
"transformer_blocks.18.attn.norm_q.weight",
"transformer_blocks.19.attn.norm_k.weight",
"transformer_blocks.19.attn.norm_q.weight",
"transformer_blocks.2.attn.norm_k.weight",
"transformer_blocks.2.attn.norm_q.weight",
"transformer_blocks.20.attn.norm_k.weight",
"transformer_blocks.20.attn.norm_q.weight",
"transformer_blocks.21.attn.norm_k.weight",
"transformer_blocks.21.attn.norm_q.weight",
"transformer_blocks.22.attn.norm_k.weight",
"transformer_blocks.22.attn.norm_q.weight",
"transformer_blocks.3.attn.norm_k.weight",
"transformer_blocks.3.attn.norm_q.weight",
"transformer_blocks.4.attn.norm_k.weight",
"transformer_blocks.4.attn.norm_q.weight",
"transformer_blocks.5.attn.norm_k.weight",
"transformer_blocks.5.attn.norm_q.weight",
"transformer_blocks.6.attn.norm_k.weight",
"transformer_blocks.6.attn.norm_q.weight",
"transformer_blocks.7.attn.norm_k.weight",
"transformer_blocks.7.attn.norm_q.weight",
"transformer_blocks.8.attn.norm_k.weight",
"transformer_blocks.8.attn.norm_q.weight",
"transformer_blocks.9.attn.norm_k.weight",
"transformer_blocks.9.attn.norm_q.weight",
"transformer_blocks.23.attn.norm_k.weight",
"transformer_blocks.23.attn.norm_q.weight",
"transformer_blocks.24.attn.norm_k.weight",
"transformer_blocks.24.attn.norm_q.weight",
"transformer_blocks.25.attn.norm_k.weight",
"transformer_blocks.25.attn.norm_q.weight",
"transformer_blocks.26.attn.norm_k.weight",
"transformer_blocks.26.attn.norm_q.weight",
"transformer_blocks.27.attn.norm_k.weight",
"transformer_blocks.27.attn.norm_q.weight",
"transformer_blocks.28.attn.norm_k.weight",
"transformer_blocks.28.attn.norm_q.weight",
"transformer_blocks.29.attn.norm_k.weight",
"transformer_blocks.29.attn.norm_q.weight",
"transformer_blocks.30.attn.norm_k.weight",
"transformer_blocks.30.attn.norm_q.weight",
"transformer_blocks.31.attn.norm_k.weight",
"transformer_blocks.31.attn.norm_q.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"
}
}