brucethemoose
/

Yi-34B-200K-RPMerge

Text Generation

text-generation-inference

Model card Files Files and versions

brucethemoose commited on Mar 4, 2024

Commit

a40931e

·

verified ·

1 Parent(s): 6873837

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -51,7 +51,7 @@ I am a huge fan of Kalomaze's quadratic sampling (shown as "smoothing factor" wh
 Otherwise, I recommend a lower temperature with 0.1 or higher MinP, a little repetition penalty, and mirostat with a low tau, and no other samplers. See the explanation here: https://github.com/ggerganov/llama.cpp/pull/3841
-@MarinaraSpaghetti has extensively tested the model and recommended the following settings, and they seem to work quite well:
 ```
 {

 Otherwise, I recommend a lower temperature with 0.1 or higher MinP, a little repetition penalty, and mirostat with a low tau, and no other samplers. See the explanation here: https://github.com/ggerganov/llama.cpp/pull/3841
+@MarinaraSpaghetti has extensively tested the model and recommended the following settings. They seem to work quite well:
 ```
 {