This model was trained on the Multi-Genre Natural Language Inference ( MultiNLI ) dataset, which consists of 433k sentence pairs textual entailment information. 

The model used is DeBERTa-v3-large from Microsoft. The v3 DeBERTa outperforms the result of Bert and RoBERTa in  majority of NLU benchmarks by using disentangled attention and enhanced mask decoder. More information about the orginal model is on official repository and the paper

This model was trained on the MultiNLI dataset, which consists of 392K sentence textual entitlement. 

DeBERTa-v3-large-mnli was trained using the Hugging Face trainer with the following hyperparameters.

Please cite the DeBERTa paper and MultiNLI Dataset if you use this model and include this Huggingface hub. 



DeBERTa-v3-large-mnli is a text classification model trained on the Multi-Genre Natural Language Inference (MultiNLI) dataset. It is based on the DeBERTa-v3-large model from Microsoft, which incorporates disentangled attention and an enhanced mask decoder to deliver improved performance compared to models like Bert and RoBERTa. The model was trained on 433k sentence pairs from the MultiNLI dataset using Hugging Face trainer and specific hyperparameters. For any use of this model, it is recommended to cite the DeBERTa paper, MultiNLI Dataset, and include the link to the Huggingface hub.

Platform did not provide a description for this model.

Khalidalt

Models by this creator

DeBERTa-v3-large-mnli

tokenizer_bpe

all-mpnet-base-v2-tasky-classification

sentence_T5_tasky_classification

Similar creators