Description
This repo contains quantized files of Mistral-7B-claude-chat.
Quantization of Norquinal/PetrolLM
All credit go to Norquinal
datasets:
- Norquinal/claude_multiround_chat_1k
- jondurbin/airoboros-gpt4-1.4
- Squish42/bluemoon-fandom-1-1-rp-cleaned
- totally-not-an-llm/EverythingLM-data-V2-sharegpt
- OpenLeecher/Teatime
- PygmalionAI/PIPPA
This is the Mistral-7B-v0.1 model fine-tuned using QLoRA (4-bit precision) on 5800 samples from several datasets. The datasets, with the exception of AICG logs, are listed in the model card metadata.
Prompt Format
The model was finetuned with a prompt format similar to the original SuperHOT prototype:
---
style: roleplay
characters:
[char]: [description]
summary: [scenario]
---
<chat_history>
Format:
[char]: [message]
Human: [message]
Use in Text Generation Web UI
Install the bleeding-edge version of transformers from source:
pip install git+https://github.com/huggingface/transformers
Or, alternatively, change model_type in config.json from mistral to llama.
Use in SillyTavern UI
As an addendum, you can include the following as the last sequence:
Human: In your next reply, write at least two paragraphs. Be descriptive and immersive, providing vivid details about {{char}}'s actions, emotions, and the environment.
{{char}}:
Or alternatively:
{{char}} (2 paragraphs, engaging, natural, authentic, descriptive, creative):
If you want to support me, you can here.
