image/png

Mahou-1.3-llama3-8B

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.

License

This model is based on Meta Llama-3-8B and is governed by the META LLAMA 3 COMMUNITY LICENSE AGREEMENT.

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

Downloads last month
6
GGUF
Model size
8.03B params
Architecture
llama

3-bit

4-bit

5-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for flammenai/Mahou-1.3-llama3-8B-GGUF

Quantized
(4)
this model

Dataset used to train flammenai/Mahou-1.3-llama3-8B-GGUF