Hugging Face's logo

DFloat11
/
Qwen-Image-DF11

Diffusers
Safetensors
qwen2_5_vl
dfloat11
df11
lossless compression
70% size, 100% accuracy
Model card Files Community
8
merve HF Staff commited on
Commit
77523c2
·
verified ·
1 Parent(s): e78d713

Improve metadata 🤗

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -1,12 +1,13 @@
1
  ---
2
  base_model:
3
- - Qwen/Qwen-Image
4
  base_model_relation: quantized
5
  tags:
6
  - dfloat11
7
  - df11
8
  - lossless compression
9
  - 70% size, 100% accuracy
 
10
  ---
11
 
12
  # DFloat11 Compressed Model: `Qwen/Qwen-Image`
@@ -160,4 +161,4 @@ Learn more in our [research paper](https://arxiv.org/abs/2504.11651).
160
 
161
  * **Paper**: [70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float](https://arxiv.org/abs/2504.11651)
162
  * **GitHub**: [https://github.com/LeanModels/DFloat11](https://github.com/LeanModels/DFloat11)
163
- * **HuggingFace**: [https://huggingface.co/DFloat11](https://huggingface.co/DFloat11)
 
1
  ---
2
  base_model:
3
+ - Qwen/Qwen-Image
4
  base_model_relation: quantized
5
  tags:
6
  - dfloat11
7
  - df11
8
  - lossless compression
9
  - 70% size, 100% accuracy
10
+ pipeline_tag: text-to-image
11
  ---
12
 
13
  # DFloat11 Compressed Model: `Qwen/Qwen-Image`
 
161
 
162
  * **Paper**: [70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float](https://arxiv.org/abs/2504.11651)
163
  * **GitHub**: [https://github.com/LeanModels/DFloat11](https://github.com/LeanModels/DFloat11)
164
+ * **HuggingFace**: [https://huggingface.co/DFloat11](https://huggingface.co/DFloat11)