turboderp
/

Mistral-7B-instruct-exl2

Model card Files Files and versions Community

turboderp commited on Sep 27, 2023

Commit

06cda4b

•

1 Parent(s): e675b6a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

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

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