FantasiaFoundry commited on
Commit
e1a7f5d
1 Parent(s): e947685

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -24,7 +24,7 @@ tags:
24
  > Try again and the conversion procress should work as expected.
25
 
26
  > [!WARNING]
27
- > **Experimental:**
28
  > There is a new experimental script added, `gguf-imat-lossless-for-BF16.py`, which performs the conversions directly from a BF16 GGUF to hopefully generate lossless, or as close to that for now, Llama-3 model quantizations avoiding the recent talked about issues on that topic, it is more resource intensive and will generate more writes in the drive as there's a whole additional conversion step that isn't performed in the previous version. This should only be necessary until we have GPU support for BF16 to run directly without conversion.
29
 
30
 
 
24
  > Try again and the conversion procress should work as expected.
25
 
26
  > [!WARNING]
27
+ > **Experimental:** <br>
28
  > There is a new experimental script added, `gguf-imat-lossless-for-BF16.py`, which performs the conversions directly from a BF16 GGUF to hopefully generate lossless, or as close to that for now, Llama-3 model quantizations avoiding the recent talked about issues on that topic, it is more resource intensive and will generate more writes in the drive as there's a whole additional conversion step that isn't performed in the previous version. This should only be necessary until we have GPU support for BF16 to run directly without conversion.
29
 
30