Intel/bert-base-uncased-mnli-sparse-70-unstructured

Sparse BERT base model fine tuned to MNLI (uncased)

Fine tuned sparse BERT base to MNLI (GLUE Benchmark) task from bert-base-uncased-sparse-70-unstructured. <br><br> Note: This model requires transformers==2.10.0

Evaluation Results

Matched: 82.5% Mismatched: 83.3%

This model can be further fine-tuned to other tasks and achieve the following evaluation results: