Hugging Face's logo

ModelsLab
/
Qwen-Image-2.1-W4A4-int4

Text-to-Image
Diffusers
Safetensors
image-to-image
quantization
w4a4
svdquant
gptq
nunchaku
8-bit precision
Model card Files
xet
 Community
1
Patil commited on
Commit
803ada5
·
verified ·
1 Parent(s): e5a7528

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -2
README.md CHANGED
@@ -77,8 +77,6 @@ pipe = QwenImage21Pipeline.from_pretrained(
77
  "Qwen/Qwen-Image-2.1", torch_dtype=torch.bfloat16, transformer=transformer)
78
  ```
79
 
80
- `nunchaku_io` and the build pipeline: https://github.com/ModelsLab/qwen-image-2-1-server
81
-
82
  ## How it was built
83
 
84
  Smoothing factors from real activation statistics (SmoothQuant, α=0.5), a rank-128 SVD
 
77
  "Qwen/Qwen-Image-2.1", torch_dtype=torch.bfloat16, transformer=transformer)
78
  ```
79
 
 
 
80
  ## How it was built
81
 
82
  Smoothing factors from real activation statistics (SmoothQuant, α=0.5), a rank-128 SVD