LeanQuant commited on
Commit
68dce0d
·
verified ·
1 Parent(s): 05a9032

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -1,3 +1,7 @@
 
 
 
 
1
  ## DFloat11 Compressed Model: `google/gemma-3-4b-it`
2
 
3
  This is a **losslessly compressed** version of [`google/gemma-3-4b-it`](https://huggingface.co/google/gemma-3-4b-it) using our custom **DFloat11** format. The outputs of this compressed model are **bit-for-bit identical** to the original BFloat16 model, while reducing GPU memory consumption by approximately **30%**.
 
1
+ ---
2
+ base_model:
3
+ - google/gemma-3-4b-it
4
+ ---
5
  ## DFloat11 Compressed Model: `google/gemma-3-4b-it`
6
 
7
  This is a **losslessly compressed** version of [`google/gemma-3-4b-it`](https://huggingface.co/google/gemma-3-4b-it) using our custom **DFloat11** format. The outputs of this compressed model are **bit-for-bit identical** to the original BFloat16 model, while reducing GPU memory consumption by approximately **30%**.