ApacheOne commited on
Commit
e48d653
·
verified ·
1 Parent(s): 84d0a95

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -6,6 +6,8 @@ tags:
6
  - df11
7
  - lossless compression
8
  - 70% size, 100% accuracy
 
 
9
  language:
10
  - en
11
  base_model:
@@ -18,4 +20,7 @@ The bf16 layers are compressed using the Dfloat11 lossless compression mixed wit
18
 
19
  This isnt the perfect balance between nvfp4 layers and Dfloat11 compressed layers and changes a good amount from model to model but it is a start.
20
 
21
- `flux-2-klein-4b-nvfp4_nvfp4_dfloat11.safetensors`
 
 
 
 
6
  - df11
7
  - lossless compression
8
  - 70% size, 100% accuracy
9
+ - 86% size 100% accuracy
10
+ - 74.4% size 100% accuracy
11
  language:
12
  - en
13
  base_model:
 
20
 
21
  This isnt the perfect balance between nvfp4 layers and Dfloat11 compressed layers and changes a good amount from model to model but it is a start.
22
 
23
+ `flux-2-klein-4b-nvfp4_nvfp4_dfloat11.safetensors`
24
+
25
+ Other models I have done get 86% size 100% accuracy doing plain Dfloat11 compression.
26
+ and around 74.4% size 100% accuracy doing nvfp4 mixed with Dfloat11 compression.