ganchengguang's picture
Update README.md
eb8ad78
metadata
license: mit
language:
  - ja
  - en
  - zh
tags:
  - LLaMA2
  - Japanese
  - LLM

This model is traned with llm-japanese-dataset dataset. And this model used a few of dataset by 50000 chat samples and 280000 non chat samples.
Improved performance in Chinese and Japanese.
Use the QLoRA to fine-tune the vanilla Llama-2-13b-chat-hf.
And you can use test.py to test the model.

Recommend Generation parameters:

  • temperature: 0.5~0.7
  • top p: 0.65~1.0
  • top k: 30~50
  • repeat penalty: 1.03~1.17

Contribute by Yokohama Nationaly University Mori Lab.