Downloads · 30 days
81
51% of all-time downloads
buddhist-nlp/nllb-200-1.3B-tib2eng
nllb-200-1.3B-tib2eng is a machine learning model from buddhist-nlp. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
This is the best scoring checkpoint on the validation set at step 4400 / 10000.
Downloads · 30 days
81
51% of all-time downloads
All-time downloads
160
Public
Repo size
11 GB
Likes
0
Public
Click a slice to open those files.
.bin5.5 GB · 100%
From the Hugging Face model README
| Training setup | |
|---|---|
| Dataset | https://huggingface.co/datasets/buddhist-nlp/tib_eng_bitext |
| Num train steps | 10000 |
| Max seq len | 256 |
| Batch size | 512 |
| Total data points seen | 5.1 mil |
| Total tokens seen | 450 mil |
This is the best scoring checkpoint on the validation set at step 4400 / 10000.
| Split | Metric | Score |
|---|---|---|
| Train | BLEU | 36.5 |
| Val | BLEU | 27.1 |
| Test | BLEU | 27.1 |
| Train | chrf++ | 52.8 |
| Val | chrf++ | 45.9 |
| Test | chrf++ | 45.6 |