Intel/bert-mini-sst2-distilled-sparse-90-1X4-block
By Intel · ↓ 7 · ♥ 1 · Updated 2022-11-23
What's in this repo
This page lists the files in Intel/bert-mini-sst2-distilled-sparse-90-1X4-block, including int8-model.onnx.
- 1 ONNX models (.onnx files)
- 11 files, including 4 .json, 2 .bin, 1 .md, 1 .onnx, 1 .yaml, 1 .txt
- Last updated 2022-11-23
ONNX files
| File | Size | Download |
|---|---|---|
| int8-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
Sparse BERT mini model (uncased)
Finetuned model pruned to 1:4 structured sparsity. The model is a pruned version of the BERT mini model.
Intended Use
The model can be used for inference with sparsity optimization. For further details on the model and its usage will be soon available.
Evaluation Results
We get the following results on the sst2 tasks development set:
| Task | SST-2 (Acc) |
|---|---|
| 87.2 | |
| Better than dense bert mini which is 84.74%. |
Model info
Created: 2022-08-16
Updated: 2022-11-23
View on Hugging Face