TheBloke
/

mpt-30B-instruct-GGML

Model card Files Files and versions Community

TheBloke commited on Jun 22, 2023

Commit

bf108b0

•

1 Parent(s): 161100d

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -59,7 +59,7 @@ Below is an instruction that describes a task. Write a response that appropriate
 The base model has an 8K context length. It is not yet confirmed if the 8K context of this model works with the quantised files.
 If it does, [KoboldCpp](https://github.com/LostRuins/koboldcpp) supports 8K context if you manually it to 8K by adjusting the text box above the slider:
-![.](https://i.imgur.com/tEbpeJq.png)
 It is currently unknown as to whether it is compatible with other clients.

 The base model has an 8K context length. It is not yet confirmed if the 8K context of this model works with the quantised files.
 If it does, [KoboldCpp](https://github.com/LostRuins/koboldcpp) supports 8K context if you manually it to 8K by adjusting the text box above the slider:
+![.](https://i.imgur.com/tEbpeJqm.png)
 It is currently unknown as to whether it is compatible with other clients.