Hugging Face's logo

DFloat11
/
BAGEL-7B-MoT-DF11

Any-to-Any
Safetensors
qwen2
dfloat11
df11
lossless compression
70% size, 100% accuracy
Model card Files Community
LeanQuant commited on
Commit
4dc3e3e
·
verified ·
1 Parent(s): 97e2fbf

Fix typo in README

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ This model uses **DFloat11** lossless compression. It's 32% smaller than the ori
16
 
17
  ### 📊 Performance Comparison
18
 
19
- | Metric | Wan2.1-T2V-14B (BFloat16) | Wan2.1-T2V-14B (DFloat11) |
20
  | ---------------------------------- | ------------------------- | ------------------------- |
21
  | Model Size | 29.21 GB | 19.89 GB |
22
  | Peak GPU Memory<br>(1024x1024 image generation) | 30.07 GB | 21.76 GB |
 
16
 
17
  ### 📊 Performance Comparison
18
 
19
+ | Metric | BAGEL-7B-MoT (BFloat16) | BAGEL-7B-MoT (DFloat11) |
20
  | ---------------------------------- | ------------------------- | ------------------------- |
21
  | Model Size | 29.21 GB | 19.89 GB |
22
  | Peak GPU Memory<br>(1024x1024 image generation) | 30.07 GB | 21.76 GB |