mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-25 15:28:59 +06:00
70f622fab4
* fix typo * rm use_cdn & references, and implement new hf_bucket_url * I'm pretty sure we don't need to `read` this file * same here * [BIG] file_utils.networking: do not gobble up errors anymore * Fix CI 😇 * Apply suggestions from code review Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Tiny doc tweak * Add doc + pass kwarg everywhere * Add more tests and explain cc @sshleifer let me know if better Co-Authored-By: Sam Shleifer <sshleifer@gmail.com> * Also implement revision in pipelines In the case where we're passing a task name or a string model identifier * Fix CI 😇 * Fix CI * [hf_api] new methods + command line implem * make style * Final endpoints post-migration * Fix post-migration * Py3.6 compat cc @stefan-it Thank you @stas00 Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> Co-authored-by: Sam Shleifer <sshleifer@gmail.com>
58 lines
2.4 KiB
Bash
Executable File
58 lines
2.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
# this script acquires data and converts it to fsmt model
|
|
# it covers:
|
|
# - facebook/wmt19-ru-en
|
|
# - facebook/wmt19-en-ru
|
|
# - facebook/wmt19-de-en
|
|
# - facebook/wmt19-en-de
|
|
|
|
# this script needs to be run from the top level of the transformers repo
|
|
if [ ! -d "src/transformers" ]; then
|
|
echo "Error: This script needs to be run from the top of the transformers repo"
|
|
exit 1
|
|
fi
|
|
|
|
mkdir data
|
|
|
|
# get data (run once)
|
|
|
|
cd data
|
|
wget https://dl.fbaipublicfiles.com/fairseq/models/wmt19.en-de.joined-dict.ensemble.tar.gz
|
|
wget https://dl.fbaipublicfiles.com/fairseq/models/wmt19.de-en.joined-dict.ensemble.tar.gz
|
|
wget https://dl.fbaipublicfiles.com/fairseq/models/wmt19.en-ru.ensemble.tar.gz
|
|
wget https://dl.fbaipublicfiles.com/fairseq/models/wmt19.ru-en.ensemble.tar.gz
|
|
tar -xvzf wmt19.en-de.joined-dict.ensemble.tar.gz
|
|
tar -xvzf wmt19.de-en.joined-dict.ensemble.tar.gz
|
|
tar -xvzf wmt19.en-ru.ensemble.tar.gz
|
|
tar -xvzf wmt19.ru-en.ensemble.tar.gz
|
|
cd -
|
|
|
|
# run conversions and uploads
|
|
|
|
export PAIR=ru-en
|
|
PYTHONPATH="src" python src/transformers/convert_fsmt_original_pytorch_checkpoint_to_pytorch.py --fsmt_checkpoint_path data/wmt19.$PAIR.ensemble/model4.pt --pytorch_dump_folder_path data/wmt19-$PAIR
|
|
|
|
export PAIR=en-ru
|
|
PYTHONPATH="src" python src/transformers/convert_fsmt_original_pytorch_checkpoint_to_pytorch.py --fsmt_checkpoint_path data/wmt19.$PAIR.ensemble/model4.pt --pytorch_dump_folder_path data/wmt19-$PAIR
|
|
|
|
export PAIR=de-en
|
|
PYTHONPATH="src" python src/transformers/convert_fsmt_original_pytorch_checkpoint_to_pytorch.py --fsmt_checkpoint_path data/wmt19.$PAIR.joined-dict.ensemble/model4.pt --pytorch_dump_folder_path data/wmt19-$PAIR
|
|
|
|
export PAIR=en-de
|
|
PYTHONPATH="src" python src/transformers/convert_fsmt_original_pytorch_checkpoint_to_pytorch.py --fsmt_checkpoint_path data/wmt19.$PAIR.joined-dict.ensemble/model4.pt --pytorch_dump_folder_path data/wmt19-$PAIR
|
|
|
|
|
|
# upload
|
|
cd data
|
|
transformers-cli upload -y wmt19-ru-en
|
|
transformers-cli upload -y wmt19-en-ru
|
|
transformers-cli upload -y wmt19-de-en
|
|
transformers-cli upload -y wmt19-en-de
|
|
cd -
|
|
|
|
# if updating just small files and not the large models, here is a script to generate the right commands:
|
|
perl -le 'for $f (@ARGV) { print qq[transformers-cli upload -y $_/$f --filename $_/$f] for map { "wmt19-$_" } ("en-ru", "ru-en", "de-en", "en-de")}' vocab-src.json vocab-tgt.json tokenizer_config.json config.json
|
|
# add/remove files as needed
|
|
|