Downloads · 30 days
14
21% of all-time downloads
GralchemOz/Qwen1.5-14B-vntl-jp2zh-4.5bpw-h6-exl2
Qwen1.5-14B-vntl-jp2zh-4.5bpw-h6-exl2 is a text generation model from GralchemOz. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as gpl-3.0.
This model is a merged version of qwen-14b-vntl and Qwen1.5-14B-Chat , aiming for the translation of Japanese context into Chinese.
Downloads · 30 days
14
21% of all-time downloads
All-time downloads
68
Public
Repo size
9.3 GB
Likes
0
Public
Click a slice to open those files.
.safetensors9.3 GB · 100%
From the Hugging Face model README
This model is a merged version of qwen-14b-vntl and Qwen1.5-14B-Chat , aiming for the translation of Japanese context into Chinese.
This repo is a quantized version in the format of .exl2, and more information about it can be found here
An examlpe of prompt is shown below:
<|im_start|>system
Please refer to the character prompts and historical information to translate the given Japanese game script into Chinese, and try to use smooth and natural expressions.<|im_end|>
<|im_start|>user
【character】
[translation of character's name]
【history】
[history of translation]
【Japanese】
[context to be translated]<|im_end|>
<|im_start|>assistant