Downloads · 30 days
17
1% of all-time downloads
castorini/duot5-3b-med-msmarco
duot5-3b-med-msmarco is a feature extraction model from castorini. Use it when you need embeddings to search or compare text. It is set up for transformers.
This model is a T5-3B reranker pre-finetuned on the MS MARCO passage dataset for 10K steps (or 1 epoch) on the pairwise task and then finetuned on MedMARCO (from Sledge-Z paper) for 1K steps on the pairwise task.
Downloads · 30 days
17
1% of all-time downloads
All-time downloads
1.6K
Public
Repo size
22.8 GB
Likes
0
Public
Click a slice to open those files.
.bin11.4 GB · 100%
From the Hugging Face model README
This model is a T5-3B reranker pre-finetuned on the MS MARCO passage dataset for 10K steps (or 1 epoch) on the pairwise task and then finetuned on MedMARCO (from Sledge-Z paper) for 1K steps on the pairwise task.
For more details on how to use it, check pygaggle.ai!
Paper describing the model: The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models