Mahou-1.3-yi-9B

Mahou is our attempt to build a production-ready conversational/roleplay LLM.

Future versions will be released iteratively and finetuned from flammen.ai conversational data.

Chat Format

This model has been trained to use ChatML format. Note the additional tokens in tokenizer_config.json.

<|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.

ST Settings

1. Use ChatML for the Context Template.
2. Enable Instruct Mode.
3. Use the Mahou preset.
4. Recommended: Add newline as a stopping string: ["\n"]

Method

Finetuned for 10 epochs using an A100 on Google Colab.

Fine-tune Llama 3 with ORPO - Maxime Labonne