Downloads · 30 days
125
19% of all-time downloads
odexine/umamusume-translator-hy-mt2-7b-gguf
umamusume-translator-hy-mt2-7b-gguf is a translation model from odexine. Use it when you need text moved from one language to another. The card lists the license as apache-2.0.
GGUF quantisations of Mario51/umamusume-translator-hy-mt2-7b, a finetune of tencent/Hy-MT2-7B
Downloads · 30 days
125
19% of all-time downloads
All-time downloads
653
Public
Repo size
39.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf39.2 GB · 100%
From the Hugging Face model README
GGUF quantisations of Mario51/umamusume-translator-hy-mt2-7b, a finetune of tencent/Hy-MT2-7B
This model was fine-tuned on a dataset created from the official English localization of the game, allowing it to capture the specific character voices, names, and tone of the Umamusume universe. It is intended to be used for translating untranslated story content.
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | Q4_K_M | 4.62 | smallest |
| GGUF | Q5_K_M | 5.37 | |
| GGUF | Q6_K_M | 6.16 | |
| GGUF | Q8_0 | 7.98 | best quality |
| GGUF | BF16 | 15 | reference |
Tencent recommends the following generation parameters for Hy-MT2 7B:
temperature: 0.7
top_p: 0.6
top_k: 20
repetition_penalty: 1.05
max_tokens: 4096
Hy-MT2 does not use a default system prompt.
The model was trained on a dataset generated by aligning the Japanese and official English story files. Thank you to the official localization team for their high-quality work which made this possible.
This model is a specialist. It may not perform well on general-purpose Japanese translation outside of the Umamusume context. It has been trained primarily on story dialogue and may not know all specific racing or training terminology.