RichardErkhov/flammenai_-_Mahou-1.3-gemma2-9B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mahou-1.3-gemma2-9B - GGUF

• —Model creator: https://huggingface.co/flammenai/
• —Original model: https://huggingface.co/flammenai/Mahou-1.3-gemma2-9B/

Original model description: --- libraryname: transformers license: gemma basemodel:

• —google/gemma-2-9b datasets:
• —flammenai/FlameMix-DPO-v1
• —flammenai/MahouMix-v1
• —flammenai/Grill-Flammen-v1_chatML ---

Mahou-1.3-gemma2-9B

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. 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.

SillyTavern Settings

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

Method

Finetuned for 3 epochs using an A100 on Google Colab.

Fine-tune Llama 3 with ORPO - Maxime Labonne