bartowski commited on
Commit
95ca489
1 Parent(s): d2c6f66

Add 8.0 link

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -24,6 +24,8 @@ Conversion was done using the default calibration dataset.
24
  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.
25
 
26
  Original model: https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
 
 
27
 
28
  ## Download instructions
29
 
 
24
  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.
25
 
26
  Original model: https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
27
+
28
+ <a href="https://huggingface.co/bartowski/Starling-LM-7B-alpha-exl2/tree/8_0">8.0 bits per weight</a>
29
 
30
  ## Download instructions
31