turboderp commited on
Commit
06cda4b
1 Parent(s): e675b6a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  EXL2 quants of Mistral-7B-instruct
2
 
3
  Converted from [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1). This is a
4
- straight conversion, but I have modified the config.json to make the default context size 7168 tokens, since in
5
  initial testing the model becomes unstable a while after that. It's possible that sliding window attention will
6
  allow the model to use its advertised 32k-token context, but this hasn't been tested yet.
7
 
 
1
  EXL2 quants of Mistral-7B-instruct
2
 
3
  Converted from [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1). This is a
4
+ straight conversion, but I have modified the `config.json` to make the default context size 7168 tokens, since in
5
  initial testing the model becomes unstable a while after that. It's possible that sliding window attention will
6
  allow the model to use its advertised 32k-token context, but this hasn't been tested yet.
7