Downloads · 30 days
15
6% of all-time downloads
lmg-anon/vntl-qwen-14b-v0.1-hf
vntl-qwen-14b-v0.1-hf is a translation model from lmg-anon. Use it when you need text moved from one language to another. It is set up for transformers. The card lists the license as other.
This is the merge of the experimental VNTL Qwen14B v0.1 qlora created using the VNTL-v3.1-1k-q dataset.
Downloads · 30 days
15
6% of all-time downloads
All-time downloads
268
Public
Parameters
14.2B
28.3 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors28.3 GB · 100%
From the Hugging Face model README
This is the merge of the experimental VNTL Qwen14B v0.1 qlora created using the VNTL-v3.1-1k-q dataset.
This is a prompt example:
<<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
<<START>>
<<JAPANESE>>
[桜乃]: 『……ごめん』
<<ENGLISH>>
[Sakuno]: 『... Sorry.』<|endoftext|>
<<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 and using load_in_4bit, is:
[Shingo]: 「It's okay, I know it sounds weird to say this, but I'm glad you got lost. You're so cute that I was worried about all sorts of things.」