Update README.md

README.md

@@ -45,6 +45,17 @@ This is the third iteration "Emerald" of the final four and the one I liked the
 
 Findings: o_proj and down_proj can be stolen from Aethora-v2 so new 15B frankenmerges don't seem to really ***need*** finetuning to "heal" the layers, though it has a big influence on the output so it's slightly censored in one-shot.
 
+# <p>Samplers</p>
+```bash
+I found success with:
+temperature 0.9
+min_p 0.08
+tfs 0.97
+smoothing_factor 0.3
+smoothing_curve 1.1
+
+```
+
 # <h1>merge</h1>
 
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).