Hugging Face's logo

rasyosef
/
splade-amharic-medium

Text Retrieval
sentence-transformers
Safetensors
Amharic
xlm-roberta
sparse-encoder
sparse
splade
Generated from Trainer
dataset_size:245876
loss:SpladeLoss
loss:SparseMultipleNegativesRankingLoss
loss:FlopsLoss
Eval Results (legacy)
Model card Files
xet
 Community
1

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

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+75
-339
nielsr

This PR improves the model card for SPLADE-Amharic-Medium by:

  1. Updating the pipeline_tag from feature-extraction to text-retrieval for better discoverability.
  2. Linking the model to the research paper: The Multilingual Curse at the Retrieval Layer: Evidence from Amharic.
  3. Adding a link to the official GitHub repository for the project.
  4. Correcting the dataset metadata in the model index.
Improve model card: update pipeline tag and add paper/code links2847d64c
rasyosef changed pull request status to merged

Sign up or log in to comment