DeBERTa v3 xsmall mnli fever anli ling binary Model description This model was trained on 782 357 hypothesis premise pairs from 4 NLI datasets: MultiNLI, Fever NLI, LingNLI and ANLI. Note that the model was trained on binary NLI to predict either "entailment" or "not entailment". This is specifically designed for zero shot classification, where the difference between "neutral" and "contradiction" is irrelevant. The base model is DeBERTa v3 xsmall from Microsoft. The v3 variant of DeBERTa substantially outperforms previous versions of the model by including a different pre training objective, see the DeBERTa V3 paper. For highest performance (but less speed), I recommend using https://huggingface.co/MoritzLaurer/DeBERTa v3 large mnli fever anli ling wanli. Intended uses & limitations How to use the model Training data This model was trained on 782 357 hypothesis premise pairs from 4 NLI datasets: MultiNLI, Fever NLI, LingNLI and ANLI. Training procedure DeBERTa v3 xsmall mnli fever anli ling binary was trained using the Hugging Face trainer with the following hyperparameters. Eval results The model was evaluated using the binary test sets for MultiNLI, ANLI, LingNLI and the binary d…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy