README.md

metadata

base_model: lemon07r/Gemma-2-Ataraxy-v4d-9B
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - gemma2
  - trl
  - sft
license: gemma
language:
  - en

This model is trained by Unsloth. This is the commission from my friend to improve the writing styles of lemon07r/Gemma-2-Ataraxy-v4d-9B in his native languages.

• Final version, I give up.
• Know issue: Short response sometime in Vietnamese, Chinese. Still speak for {{user}} sometimes.
• Pros: Long response in english, good writing styles(?), and I fixed the issue that it will repeat sentence at the end of responses.
• Cons: short response in Vietnamese, Chinese, Japanese due to the dataset is novel chapter, short sentence in 1 row. :/.