Text Generation
Safetensors
mistral
conversational
Epiculous commited on
Commit
a4ee461
1 Parent(s): 5ac31ff

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -33,7 +33,8 @@ Crimson Dawn was trained with the Mistral Instruct template, therefore it should
33
  ### Context and Instruct
34
  [Mistral-Custom-Context.json](https://files.catbox.moe/l9w0ry.json) <br/>
35
  [Mistral-Custom-Instruct.json](https://files.catbox.moe/9xiiwb.json)
36
-
 
37
 
38
  ### Current Top Sampler Settings
39
  [Crimson_Dawn-Nitral-Special](https://files.catbox.moe/8xjxht.json) - Considered the best settings! <br/>
 
33
  ### Context and Instruct
34
  [Mistral-Custom-Context.json](https://files.catbox.moe/l9w0ry.json) <br/>
35
  [Mistral-Custom-Instruct.json](https://files.catbox.moe/9xiiwb.json)
36
+ *** NOTE ***
37
+ There have been reports of the quantized model misbehaving with the mistral prompt, if you are seeing issues it may be worth trying ChatML Context and Instruct templates.
38
 
39
  ### Current Top Sampler Settings
40
  [Crimson_Dawn-Nitral-Special](https://files.catbox.moe/8xjxht.json) - Considered the best settings! <br/>