Update README.md

README.md

@@ -20,7 +20,7 @@ datasets:
 - Gryphe/Sonnet3.5-SlimOrcaDedupCleaned
 - mpasila/Sonnet3.5-SlimOrcaDedupCleaned-4k-context
 ---
-This is a test model because the previous attempt failed. So it turns out I also trained this incorrectly due to the dataset using wrongly formatted ShareGPT so after I trained this "correctly" for another full epoch I noticed that so.. I will have to train it yet again.. but at least now it should be fixed. But this model is using the wrongly formatted dataset. The next model should be better.
+This is a test model because the previous attempt failed. So it turns out I also trained this incorrectly due to the dataset using wrongly formatted ShareGPT so after I trained it again "correctly" for another full epoch I noticed that so.. I will have to train it yet again.. but at least now it should be fixed. But this model is using the wrongly formatted dataset. The next model should be better.
 
 Prompt format is: ChatML