nli
3 TagsUpdated MITby Moritz Laurer
Zero-shot classifiers by Moritz Laurer: every option becomes a hypothesis scored for entailment. The most accurate encoder model on typed decisions in our tests.
zero-shot396m435m
Tags
| Name |
|---|
| nlilatestSame as nli:deberta-v3-large.884 MB · 512 ctx · English |
| nli:deberta-v3-largeDeBERTa-v3-large, MIT. Most accurate encoder in our tests (0.548 on typed decisions).884 MB · 512 ctx · English |
| nli:modernbert-largeModernBERT-large, Apache-2.0. Faster, slightly less accurate (0.515).799 MB · 512 ctx · English |
Tags without a suffix load fp16 on a CUDA GPU and fp32 on CPU; add -fp16 or -fp32 to pin one precision.