distilbert-imdb
This model is a fine-tuned version of distilbert-base-uncased on the imdb dataset (training notebook is here). It achieves the following results on the evaluation set: - Loss: 0.1903 - Accuracy: 0.928
Params
—
Context
512
Downloads 30d
337 K
Likes
25
Download history
daily snapshots · 55 days
▲ 146 K in the last 30 days (30.3%)
621 K337 K
Aug 22Sep 1Sep 11Sep 20
621 K225 K
Jul 28Aug 15Sep 2Sep 20
Specifications
- Architecture
- DistilBertForSequenceClassification
- Context length
- 512
- Vocabulary
- 30,522
- Licence
- apache-2.0
- First seen on the Hub
- 2022-03-02
- Training datasets
- imdb
- imdb (reported)
- 0.928
- Added to our catalog
- 2026-07-28
Compare with any text-classification model