Text Generation
Transformers
PyTorch
mistral
Not-For-All-Audiences
nsfw
text-generation-inference
Inference Endpoints
Norquinal's picture
Update README.md
3d7121a
metadata
datasets:
  - Squish42/bluemoon-fandom-1-1-rp-cleaned
  - OpenLeecher/Teatime
  - PygmalionAI/PIPPA
tags:
  - not-for-all-audiences
  - nsfw
license: cc-by-nc-4.0

What is PetrolLM-Claude-Chat?

PetrolLM-Claude-Chat is the Mistral-7B-claude-chat model with the PetrolLoRA applied.

The dataset (for the LoRA) consists of 2800 samples, with the composition as follows:

  • AICG Logs (~34%)
  • PygmalionAI/PIPPA (~33%)
  • Squish42/bluemoon-fandom-1-1-rp-cleaned (~29%)
  • OpenLeecher/Teatime (~4%)

These samples were then back-filled using gpt-4/gpt-3.5-turbo-16k or otherwise converted to fit the prompt format.

Prompt Format

The model uses the following prompt format: ```

style: roleplay characters: [char]: [description] summary: [scenario]

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 one of the following as the Last Output 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}}:
{{char}} (2 paragraphs, engaging, natural, authentic, descriptive, creative):
[System note: Write at least two paragraphs. Be descriptive and immersive, providing vivid details about {{char}}'s actions, emotions, and the environment.]
{{char}}:

The third one seems to work the best. I would recommend experimenting with creating your own to best suit your needs.