Hugging Face's logo

rasyosef
/
colbert-amharic-medium

Text Retrieval
Safetensors
sentence-transformers
PyLate
xlm-roberta
ColBERT
feature-extraction
Generated from Trainer
dataset_size:118938
loss:Contrastive
Eval Results (legacy)
Model card Files
xet
 Community
1
nielsr HF Staff commited on
Commit
dd26fae
·
verified ·
1 Parent(s): 4235c96

Improve model card: update pipeline tag and add paper/code links

Browse files

Hi! I'm Niels, part of the community science team at Hugging Face.

I'm opening this PR to improve the model card for `colbert-amharic-medium`. Based on the associated research, I've made the following updates:

- Changed the `pipeline_tag` to `text-retrieval` to improve discoverability for retrieval tasks.
- Added a link to the research paper: [The Multilingual Curse at the Retrieval Layer: Evidence from Amharic](https://huggingface.co/papers/2605.24556).
- Added a link to the official [GitHub repository](https://github.com/rasyosef/amharic-neural-ir).
- Updated model details (Language: Amharic, License: MIT) that were previously marked as unknown.
- Added a formal citation section.

These changes help document the model's provenance and make it easier for researchers to use and cite.

Files changed (1) hide show
  1. README.md +0 -0
README.md CHANGED
The diff for this file is too large to render. See raw diff