Spaces:

FastFit
/

README

Running

Elron commited on Apr 18

Commit

ceb603e

•

1 Parent(s): c7472e3

Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

@@ -8,9 +8,7 @@ pinned: true
 license: apache-2.0
 short_description: Fast and Effective Text Classification with Many Classes
 ---
-![fastfit_banner_white](https://github.com/IBM/fastfit/assets/23455264/a4de0a5e-b43a-462b-b1f2-9509ec873e76)
 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.

 license: apache-2.0
 short_description: Fast and Effective Text Classification with Many Classes
 ---
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5fc0292de45c5468456e022b/A-XcHLZlq2QYckIckA_d8.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.