mlabonne commited on
Commit
c362a1b
·
verified ·
1 Parent(s): cd7a097

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -139,10 +139,14 @@ Special thanks to [Jon Durbin](https://huggingface.co/jondurbin), [Intel](https:
139
 
140
  This model uses a context window of 8k. I recommend using it with the Mistral Instruct chat template (works perfectly with LM Studio).
141
 
 
 
142
  It is one of the very best 7B models in terms of instructing following and reasoning abilities and can be used for conversations, RP, and storytelling. Note that it tends to have a quite formal and sophisticated style, but it can be changed by modifying the prompt.
143
 
144
  ## ⚡ Quantized models
145
 
 
 
146
  * **GGUF**: https://huggingface.co/mlabonne/AlphaMonarch-7B-GGUF
147
  * **GPTQ**: https://huggingface.co/LoneStriker/AlphaMonarch-7B-GPTQ
148
  * **AWQ**: https://huggingface.co/LoneStriker/AlphaMonarch-7B-AWQ
 
139
 
140
  This model uses a context window of 8k. I recommend using it with the Mistral Instruct chat template (works perfectly with LM Studio).
141
 
142
+ If you use SillyTavern, you might want to tweak the inference parameters. Here's what LM Studio uses as a reference: `temp` 0.8, `top_k` 40, `top_p` 0.95, `min_p` 0.05, `repeat_penalty` 1.1.
143
+
144
  It is one of the very best 7B models in terms of instructing following and reasoning abilities and can be used for conversations, RP, and storytelling. Note that it tends to have a quite formal and sophisticated style, but it can be changed by modifying the prompt.
145
 
146
  ## ⚡ Quantized models
147
 
148
+ Thanks to [LoneStriker](https://huggingface.co/LoneStriker) for the GPTQ, AWQ, and EXL2 quants.
149
+
150
  * **GGUF**: https://huggingface.co/mlabonne/AlphaMonarch-7B-GGUF
151
  * **GPTQ**: https://huggingface.co/LoneStriker/AlphaMonarch-7B-GPTQ
152
  * **AWQ**: https://huggingface.co/LoneStriker/AlphaMonarch-7B-AWQ