rasyosef/Amharic-Passage-Retrieval-Dataset-V2 download history
rasyosef/Amharic-Passage-Retrieval-Dataset-V2 is a text retrieval dataset on the Hugging Face Hub. In the last 30 days it was downloaded 84 times (11 in the last 7 days), and 1,195 times in total. It ranks #172,736 among datasets by monthly downloads.
Amharic Passage Retrieval Dataset V2 This dataset is the official benchmark for the paper "The Multilingual Curse at the Retrieval Layer: Evidence from Amharic". It provides a fixed 90/10 train–test split consisting of 68,000 query–passage pairs, specifically designed for evaluating a
Models trained on Amharic-Passage-Retrieval-Dataset-V2
8 models list it as training data.
- rasyosef/embedding-amharic-medium 50 downloads in 30 days
- rasyosef/reranker-amharic-base 47 downloads in 30 days
- rasyosef/embedding-amharic-base 37 downloads in 30 days
- rasyosef/splade-amharic-base 32 downloads in 30 days
- rasyosef/reranker-amharic-medium 30 downloads in 30 days
- rasyosef/splade-amharic-medium 28 downloads in 30 days
- rasyosef/colbert-amharic-base 22 downloads in 30 days
- rasyosef/colbert-amharic-medium 21 downloads in 30 days
Open rasyosef/Amharic-Passage-Retrieval-Dataset-V2 on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.