Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456
FastFit (FastFit)
[go: Go Back, main page]
Hugging Face's logo
Activity Feed
\"image/png\"

\n

FastFit, a method, and a Python package design to provide fast and accurate few-shot classification, especially for scenarios with many semantically similar classes. FastFit utilizes a novel approach integrating batch contrastive learning and token-level similarity score. Compared to existing few-shot learning packages, such as SetFit, Transformers, or few-shot prompting of large language models via API calls, FastFit significantly improves multi-class classification performance in speed and accuracy across FewMany, our newly curated English benchmark, and Multilingual datasets. FastFit demonstrates a 3-20x improvement in training speed, completing training in just a few seconds.

\n
pip install fast-fit\n
\n","classNames":"hf-sanitized hf-sanitized-oitRDB6rXwduHEoOyf8bD"},"users":[{"_id":"5fc0292de45c5468456e022b","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5fc0292de45c5468456e022b/MEuHFEf6LtTbcptc0heoM.png","isPro":false,"fullname":"Elron Bandel","user":"Elron","type":"user"},{"_id":"638324f862badff43269e588","avatarUrl":"/avatars/907a39a9b44fc8b7f3fad35858b01fb7.svg","isPro":false,"fullname":"Asaf Yehudai","user":"Asaf-Yehudai","type":"user"},{"_id":"64e39156384b85306bdcbfa8","avatarUrl":"/avatars/c638f87a28ab201066553634b3ea87a7.svg","isPro":false,"fullname":"Amrith Krishna","user":"krishnamrithCam","type":"user"}],"userCount":3,"collections":[],"datasets":[{"author":"FastFit","downloads":93,"gated":false,"id":"FastFit/claim_stance_55","lastModified":"2024-03-21T08:03:35.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2155,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":1,"isLikedByUser":false,"isBenchmark":false}],"models":[],"paperPreviews":[],"spaces":[],"buckets":[],"numBuckets":0,"numDatasets":1,"numModels":0,"numSpaces":1,"lastOrgActivities":[],"acceptLanguages":["*"],"canReadRepos":false,"canReadSpaces":false,"blogPosts":[],"currentRepoPage":0,"filters":{},"paperView":false}">

AI & ML interests

None defined yet.

Organization Card
Community About org cards

image/png

FastFit, a method, and a Python package design to provide fast and accurate few-shot classification, especially for scenarios with many semantically similar classes. FastFit utilizes a novel approach integrating batch contrastive learning and token-level similarity score. Compared to existing few-shot learning packages, such as SetFit, Transformers, or few-shot prompting of large language models via API calls, FastFit significantly improves multi-class classification performance in speed and accuracy across FewMany, our newly curated English benchmark, and Multilingual datasets. FastFit demonstrates a 3-20x improvement in training speed, completing training in just a few seconds.

pip install fast-fit

models 0

None public yet