Create README.md

README.md

@@ -0,0 +1,7 @@
+Mistral-7B finetuned on a dataset of BTS fanfic at 32k context.
+
+This model uses the alpaca format:
+```
+{"instruction": "An interaction between a user providing instructions, and an imaginative assistant providing responses.", "input": "...", "output": "..."}
+```
+Note RoPE scaling parameter **8.0**, with RoPE scaling type linear