vuiseng9/bert-base-squadv1-pruneofa-90pc-bt
By vuiseng9 · ↓ 1 · ♥ 0 · Updated 2022-01-18
What's in this repo
This page lists the files in vuiseng9/bert-base-squadv1-pruneofa-90pc-bt, including bert-base-squadv1-pruneofa-90pc-bt.onnx.
- 1 ONNX models (.onnx files)
- 39 files, including 16 .json, 9 .bin, 3 .md, 2 .pt, 2 .txt, 2 .csv
- Last updated 2022-01-18
ONNX files
| File | Size | Download |
|---|---|---|
| bert-base-squadv1-pruneofa-90pc-bt.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
This model is transfer-learning of bert-base pruneofa 90% sparse on Squadv1 dataset.
eval_exact_match = 80.2933
eval_f1 = 87.6788
eval_samples = 10784
Train
use https://github.com/IntelLabs/Model-Compression-Research-Package.git
see pruneofa-transfer-learning.sh
Eval
export CUDA_VISIBLE_DEVICES=0
OUTDIR=eval-bert-base-squadv1-pruneofa-90pc-bt
WORKDIR=transformers/examples/pytorch/question-answering
cd $WORKDIR
nohup python run_qa.py \
--model_name_or_path vuiseng9/bert-base-squadv1-pruneofa-90pc-bt \
--dataset_name squad \
--do_eval \
--per_device_eval_batch_size 128 \
--max_seq_length 384 \
--doc_stride 128 \
--overwrite_output_dir \
--output_dir $OUTDIR 2>&1 | tee $OUTDIR/run.log &
Model info
Created: 2022-03-02
Updated: 2022-01-18
View on Hugging Face