Edit model card

Summary

This repository contains the merged VNTL LLaMA3 8B 202409 qlora, created using a custom version of the VNTL dataset combined with the VNTL-Chat dataset.

The purpose of this model is to improve LLaMA3's performance at translating Japanese visual novels to English, but the model also includes a "chat mode", which primarily works for Japanese grammar questions.

For more information about this model, please check out the original repository.

Translation Prompt

This is an prompt example for translation:

<<METADATA>>
[character] Name: Uryuu Shingo (η“œη”Ÿ 新吾) | Gender: Male | Aliases: Onii-chan (γŠε…„γ‘γ‚ƒγ‚“)
[character] Name: Uryuu Sakuno (η“œη”Ÿ ζ‘œδΉƒ) | Gender: Female
<<TRANSLATE>>
<<JAPANESE>>
[ζ‘œδΉƒ]: γ€Žβ€¦β€¦γ”γ‚γ‚“γ€
<<ENGLISH>>
[Sakuno]: γ€Ž... Sorry.』<|end_of_text|>
<<JAPANESE>>
[新吾]: γ€Œγ†γ†γ‚“γ€γ“γ†θ¨€γ£γ‘γ‚ƒγͺγ‚“γ γ‘γ©γ€θΏ·ε­γ§γ‚ˆγ‹γ£γŸγ‚ˆγ€‚ζ‘œδΉƒγ―ε―ζ„›γ„γ‹γ‚‰γ€γ„γ‚γ„γ‚εΏƒι…γ—γ‘γ‚ƒγ£γ¦γŸγ‚“γ γžδΏΊγ€
<<ENGLISH>>

The generated translation for that prompt, with temperature 0, is:

[Shingo]: γ€ŒNo, I'm glad you got lost. You're so cute that it made me worry a lot.」

Chat Prompt

This is an prompt example for chat:

<<CHAT>>
<<HUMAN>>
Hi! Can you break this down to me? Like, what is the meaning of "ζ‘œδΉƒγ―ε―ζ„›γ„γ‹γ‚‰"?
"ううん、こう言っけゃγͺγ‚“γ γ‘γ©γ€θΏ·ε­γ§γ‚ˆγ‹γ£γŸγ‚ˆγ€‚ζ‘œδΉƒγ―ε―ζ„›γ„γ‹γ‚‰γ€γ„γ‚γ„γ‚εΏƒι…γ—γ‘γ‚ƒγ£γ¦γŸγ‚“γ γžδΏΊγ€"
<<LLM>>

The generated response for that prompt, with temperature 0, is:

Certainly! The phrase "ζ‘œδΉƒγ―ε―ζ„›γ„γ‹γ‚‰" can be broken down as follows:
"ζ‘œδΉƒ" (Sakurano) is a proper noun, likely referring to a person's name.
"は" (wa) is a particle that marks the topic or subject of the sentence.
"可愛い" (kawaii) means "cute" or "adorable."
"から" (kara) is a conjunction that indicates a reason or cause.
So, the entire phrase "ζ‘œδΉƒγ―ε―ζ„›γ„γ‹γ‚‰" translates to "Because Sakurano is cute." This suggests that the speaker finds Sakurano to be endearing or charming in some way.
Downloads last month
2
Safetensors
Model size
8.03B params
Tensor type
BF16
Β·
Inference Examples
Inference API (serverless) does not yet support peft models for this pipeline type.

Model tree for lmg-anon/vntl-llama3-8b-202409-hf

Adapter
(5)
this model

Dataset used to train lmg-anon/vntl-llama3-8b-202409-hf