nbeerbower's picture
Update README.md
e0412c4 verified
|
raw
history blame
1.26 kB
metadata
library_name: transformers
license: llama3
base_model:
  - nbeerbower/llama-3-SNAMD-8B
datasets:
  - flammenai/MahouMix-v1
  - flammenai/FlameMix-DPO-v1

image/png

Mahou-1.3b-llama3-8B

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 preset.
  4. Recommended Additonal stopping strings: ["\n", "<|", "</"]

Method

ORPO finetuned on 2x RTX 4060 Ti for 1 epoch.

Fine-tune Llama 3 with ORPO