bartowski commited on
Commit
d86ffdc
1 Parent(s): 6ce0437

Add 8.0 link

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -36,6 +36,8 @@ Conversion was done using the default calibration dataset.
36
  Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
37
 
38
  Original model: https://huggingface.co/rishiraj/CatPPT
 
 
39
 
40
  ## Download instructions
41
 
 
36
  Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
37
 
38
  Original model: https://huggingface.co/rishiraj/CatPPT
39
+
40
+ <a href="https://huggingface.co/bartowski/CatPPT-exl2/tree/8_0">8.0 bits per weight</a>
41
 
42
  ## Download instructions
43