How to use this model directly from the
from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("prajjwal1/bert-mini-mnli") model = AutoModelForSequenceClassification.from_pretrained("prajjwal1/bert-mini-mnli")
The following model is a Pytorch pre-trained model obtained from converting Tensorflow checkpoint found in the official Google BERT repository. These BERT variants were introduced in the paper Well-Read Students Learn Better: On the Importance of Pre-training Compact Models. These models are trained on MNLI.
MNLI: 68.04% MNLI-mm: 69.17%
These models were trained for 4 epochs.