Downloads · 30 days
0
cantonese-alma-2-7b-oasst-v1-lora
superaidesu/cantonese-alma-2-7b-oasst-v1-lora
cantonese-alma-2-7b-oasst-v1-lora is a machine learning model from superaidesu. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama2.
Base model: https://huggingface.co/indiejoseph/cantonese-llama-2-7b-oasst-v1
Access
Public
Updated Dec 5, 2023
Repo size
15.5 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin15.5 MB · 100%
At a glance
- License
- llama2
- Access
- Public
- Created
- Nov 23, 2023
- Updated
- Dec 5, 2023
- SHA
- 3b6b1780
Model card
From the Hugging Face model README
Base model: https://huggingface.co/indiejoseph/cantonese-llama-2-7b-oasst-v1
Finetuned following ALMA (https://github.com/fe1ixxu/ALMA) on the Cantonese-Mandarin translation task.
Finetuning dataset: Sourced from the released raw dataset in https://github.com/meganndare/cantonese-nlp
As the base model was already finetuned on Cantonese monolingual data, we only conducted finetuning on parallel sentences.
Results:
Man -> Can: 35.371 BLEU, 26.197 ChrF++
Can -> Man: 36.553 BLEU, 27.471 ChrF++
Github Repo: https://github.com/cmgao/nlp_project
The ALMA code was linked as submodule.
- License
- llama2
- Languages
- zh
- Created
- Nov 23, 2023
- Updated
- Dec 5, 2023