Update README.md

README.md

@@ -11,6 +11,14 @@ language:
 - en
 ---
 
+A Fishy Model
+
+This model was trained with SFT using Unsloth on the ChatML format with 8k context. Carp models are trained with a combination of pretrain, instruct, and chat datasets.
+
+# Changes
+- Training dataset had some "slop" and refusals removed.
+- Datasets were reformatted.
+
 # Uploaded  model
 
 - **Developed by:** TheTsar1209