TheBloke commited on
Commit
b1c0cfa
·
1 Parent(s): 1e3e5b0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -49,7 +49,9 @@ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization metho
49
 
50
  These are experimental first AWQs for the brand-new model format, Mistral.
51
 
52
- They will not work from vLLM or TGI. They can only be used from AutoAWQ, and they require installing both AutoAWQ and Transformers from Github. More details are below.
 
 
53
 
54
  <!-- description end -->
55
  <!-- repositories-available start -->
@@ -66,7 +68,6 @@ They will not work from vLLM or TGI. They can only be used from AutoAWQ, and the
66
 
67
  ```
68
  <s>[INST] {prompt} [/INST]
69
-
70
  ```
71
 
72
  <!-- prompt-template end -->
 
49
 
50
  These are experimental first AWQs for the brand-new model format, Mistral.
51
 
52
+ As of September 29th 2023, they are supported by AutoAWQ, and vLLM (version 0.2).
53
+
54
+ To use from AutoAW£Q requires installing both AutoAWQ and Transformers from Github. More details are below.
55
 
56
  <!-- description end -->
57
  <!-- repositories-available start -->
 
68
 
69
  ```
70
  <s>[INST] {prompt} [/INST]
 
71
  ```
72
 
73
  <!-- prompt-template end -->