Downloads · 30 days
92
50% of all-time downloads
transalign-nllb-200-distilled-600M
haukurpj/transalign-nllb-200-distilled-600M
transalign-nllb-200-distilled-600M is a machine learning model from haukurpj. 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 peft. The card lists the license as apache-2.0.
This is a LoRA adapter for word alignment, applied to the encoder of facebook/nllb-200-distilled-600M.
All-time downloads
185
Public
Repo size
3.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.9 MB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Mar 26, 2026
- Updated
- Mar 26, 2026
- SHA
- 8ccf6100
Base models
Model card
From the Hugging Face model README
TransAlign LoRA Adapter for NLLB-200-distilled-600M
This is a LoRA adapter for word alignment, applied to the encoder of facebook/nllb-200-distilled-600M.
This adapter was not created by the uploader. It is redistributed here for convenience. All credit belongs to the original authors.
Original Authors
- Benedikt Ebing, Christian Goldschmied, and Goran Glavaš
Paper
TransAlign: Machine Translation Encoders are Strong Word Aligners, Too Findings of the Association for Computational Linguistics: EMNLP 2025, pages 20736-20749. https://aclanthology.org/2025.findings-emnlp.1129/
Source Code
https://github.com/bebing93/transalign
License
The original repository is licensed under Apache 2.0.
- Library
- peft
- License
- apache-2.0
- Created
- Mar 26, 2026
- Updated
- Mar 26, 2026