Update README.md

README.md

@@ -7,9 +7,7 @@ datasets:
 - OpenLeecher/Teatime
 - PygmalionAI/PIPPA
 ---
-This is the [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) model fine-tuned using QLoRA (4-bit precision) on my [claude_multiround_chat_1k](https://huggingface.co/datasets/Norquinal/claude_multiround_chat_1k) dataset, which is a randomized subset of ~1000 samples from my [claude_multiround_chat_30k](https://huggingface.co/datasets/Norquinal/claude_multiround_chat_30k) dataset.
-
-Do not take this model very seriously, it is probably not very good. I haven't a clue of what I'm doing. I just thought it was a fun thing to make.
+This is the [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) model fine-tuned using QLoRA (4-bit precision) on 5800 samples from the datasets:
 
 ## Prompt Format
 The model was finetuned with a prompt format similar to the original SuperHOT prototype:
@@ -21,6 +19,9 @@ characters:
 summary: [scenario]
 ---
 <chat_history>
+Format:
+[Name]: [Message]
+Human: [Message]
 ```
 
 ## Use in Text Generation Web UI