Update README.md

README.md

@@ -28,10 +28,9 @@ inference:
   parameters:
     temperature: 0.4
     do_sample: True
-    top_p: 0.14
-    top_k: 21
+    top_p: 0.34
+    top_k: 30
     max_new_tokens: 250
-    repetition_penalty: 1.14
 ---
 Base model Locutusque/TinyMistral-248M fully fine-tuned on Locutusque/InstructMix. During validation, this model achieved an average perplexity of 3.23 on Locutusque/InstructMix dataset.
 It has so far been trained on approximately 608,000 examples. More epochs are planned for this model.