jhu-clsp / ettin-encoder-400m
Other39.2K14Updated Jul 16, 2025
Downloads
39.2K
Likes
14
Last updated
Jul 16, 2025
License
mit
šÆ TL;DR: State-of-the-art paired encoder and decoder models (17M-1B params) trained identically for fair comparison with open data. Encoders beat ModernBERT. Decoders beat Llama 3.2/SmolLM2.
Tasks & library
- fill mask
Tags
- pytorch
- modernbert
- fill-mask
- en
Technical specifications
ParametersNot available
LibraryNot available
Languagesen
Licensemit