nbeerbower's picture
Update README.md
38ea056 verified
metadata
library_name: transformers
license: apache-2.0
base_model:
  - mistralai/Mistral-Nemo-Instruct-2407
datasets:
  - flammenai/MahouMix-v1
  - flammenai/FlameMix-DPO-v1

image/png

Mahou-1.3-mistral-nemo-12B

Mahou is designed to provide short messages in a conversational context. It is capable of casual conversation and character roleplay.

Chat Format

This model has been trained to use ChatML format.

<|im_start|>system
{{system}}<|im_end|>
<|im_start|>{{char}}
{{message}}<|im_end|>
<|im_start|>{{user}}
{{message}}<|im_end|>

Roleplay Format

  • Speech without quotes.
  • Actions in *asterisks*
*leans against wall cooly* so like, i just casted a super strong spell at magician academy today, not gonna lie, felt badass.

SillyTavern Settings

  1. Use ChatML for the Context Template.
  2. Enable Instruct Mode.
  3. Use the Mahou ChatML Instruct preset.
  4. Recommended Additonal stopping strings: ["\n", "<|", "</"]
  5. Use the Mahou Sampler preset.

Method

ORPO finetuned on a Google Colab A100 for 1 epoch.

Fine-tune Llama 3 with ORPO