README.md

---
license: gemma
datasets:
- lmg-anon/VNTL-v3.1-1k
language:
- ja
- en
library_name: peft
base_model: rinna/gemma-2-baku-2b
pipeline_tag: translation
---

# Summary

his repository contains some GGUF quantizations of the merged [VNTL Gemma2 2B lora](https://huggingface.co/lmg-anon/vntl-gemma2-2b-lora), created using the [VNTL 3.1 dataset](https://huggingface.co/datasets/lmg-anon/VNTL-v3.1-1k).

The purpose of this model is to improve Gemma2's performance at translating Japanese visual novels to English.

For more information about this model, please check out the [original repository](https://huggingface.co/lmg-anon/vntl-gemma2-2b-lora).

## Translation Prompt

This is an prompt example for translation:
```
<<METADATA>>
[character] Name: Uryuu Shingo (瓜生 新吾) | Gender: Male | Aliases: Onii-chan (お兄ちゃん)
[character] Name: Uryuu Sakuno (瓜生 桜乃) | Gender: Female
<<TRANSLATE>>
<<JAPANESE>>
[桜乃]: 『……ごめん』
<<ENGLISH>>
[Sakuno]: 『... Sorry.』<eos>
<<JAPANESE>>
[新吾]: 「ううん、こう言っちゃなんだけど、迷子でよかったよ。桜乃は可愛いから、いろいろ心配しちゃってたんだぞ俺」
<<ENGLISH>>
```

The generated translation for that prompt, with temperature 0, is:
```
[Shingo]: 「No, I'm glad you got lost. You were so cute that it made me worry.」
```