Update README.md

README.md

@@ -1,4 +1,4 @@
-LoRA for OPT-1.3b, finetuned for chat
+LoRA for OPT-1.3b, finetuned for chatting. Note that this model is meant to be conversation tuned, NOT instruct tuned.
 
 Trained on a selection of data from https://www.kaggle.com/datasets/jef1056/discord-data
 
@@ -9,6 +9,20 @@ Prompting format:
 [Person 1]:
 ```
 
+Example chat:
+```
+human: hello
+bot: hi how are you?
+human: good, you?
+bot: I'm doing alright. How about yourself?
+human: what are you doing now?
+bot: just watching netflix and playing games. What about you?
+human: nothing much
+bot: same here
+human: write me a poem
+bot: ok i will do it when im not on my phone
+```
+
 Training params:
 ```py
 transformers.TrainingArguments(