Task
Other
P
minishlab/potion-retrieval-32M
Other·minishlab· 123.3K· 29
model2vec
mit
Other
32.3M params
dataset:sentence-transformers/gooaqdataset:sentence-transformers/msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1dataset:sentence-transformers/squaddataset:sentence-transformers/s2orcdataset:sentence-transformers/all-nli
This Model2Vec model is optmized for retrieval tasks. It is a finetune of potion-base-32M. It's finetuned using a modified version of the training approach described in this blogpost. It uses static embeddings, allowing text embeddings to be computed orders of magnitude faster on both GPU and CPU. It is designed for applications where computational resources are limited or where real-time performa
# pull & run locally
pip install mlforge-sdk && mlforge pull minishlab/potion-retrieval-32M
pip install mlforge-sdk && mlforge pull minishlab/potion-retrieval-32M
Model details
Provider
minishlab
Framework
model2vec
Parameters
32.3M
Size
246 MB
License
mit
Downloads
123.3K
Likes
29
Updated
2026-03-27
About minishlab/potion-retrieval-32M
This Model2Vec model is optmized for retrieval tasks. It is a finetune of potion-base-32M. It's finetuned using a modified version of the training approach described in this blogpost. It uses static embeddings, allowing text embeddings to be computed orders of magnitude faster on both GPU and CPU. It is designed for applications where computational resources are limited or where real-time performance is critical.