Update README.md

README.md

@@ -1,6 +1,8 @@
 ---
 inference: false
 license: other
+datasets:
+- gozfarb/ShareGPT_Vicuna_unfiltered
 ---
 
 <div style="width: 100%;">
@@ -77,3 +79,27 @@ Donaters will get priority support on any and all AI/LLM/model questions, and I'
 * Discord: https://discord.gg/UBgz4VXf
 
 # Original model card: Aeala's VicUnlocked Alpaca 65B QLoRA
+
+
+## LoRA Info:
+Please note that this is a highly experimental LoRA model. It may do some good stuff, it might do some undesirable stuff. Training is paused for now. Feel free to try it!~
+
+**Important Note**: While this is trained on a cleaned ShareGPT dataset like Vicuna used, this was trained in the *Alpaca* format, so prompting should be something like:
+
+```
+### Instruction:
+
+<prompt> (without the <>)
+
+### Response:
+```
+
+Current upload: checkpoint of step 1200 in training.
+
+
+## Benchmarks
+**wikitext2:** Coming soon...
+
+**ptb-new:** Coming soon...
+
+**c4-new:** Coming soon...