Intel/bert-large-uncased-squadv1.1-sparse-80-1x4-block-pruneofa
By Intel · ↓ 9 · ♥ 1 · Updated 2022-08-01
What's in this repo
This page lists the files in Intel/bert-large-uncased-squadv1.1-sparse-80-1x4-block-pruneofa, including model.onnx.
- 1 ONNX models (.onnx files)
- 9 files, including 4 .json, 1 .md, 1 .onnx, 1 .bin, 1 .txt
- Last updated 2022-08-01
ONNX files
| File | Size | Download |
|---|---|---|
| model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
80% 1x4 Block Sparse BERT-Large (uncased) Fine Tuned on SQuADv1.1
This model is a result of fine-tuning a Prune OFA 80% 1x4 block sparse pre-trained BERT-Large combined with knowledge distillation. This model yields the following results on SQuADv1.1 development set:
{"exact_match": 84.673, "f1": 91.174}
For further details see our paper, Prune Once for All: Sparse Pre-Trained Language Models, and our open source implementation available here.
Model info
Created: 2022-03-27
Updated: 2022-08-01
View on Hugging Face