SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Update legacy Repository usage in various example files (#29085)

Browse Source 
* Update legacy Repository usage in `examples/pytorch/text-classification/run_glue_no_trainer.py`

Marked for deprecation here https://huggingface.co/docs/huggingface_hub/guides/upload#legacy-upload-files-with-git-lfs

* Fix import order

* Replace all example usage of deprecated Repository

* Fix remaining repo call and rename args variable

* Revert removing creation of gitignore files and don't change research examples
This commit is contained in:
Hilco van der Wilk
2024-03-12 14:20:49 +01:00
committed by GitHub
parent f1a565a39f
commit b6404866cd
24 changed files with 338 additions and 163 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
examples/flax/token-classification/run_flax_ner.py
View File

@@ -39,7 +39,7 @@ from flax import struct, traverse_util
from flax.jax_utils import pad_shard_unpad, replicate, unreplicate
from flax.training import train_state
from flax.training.common_utils import get_metrics, onehot, shard
from huggingface_hub import Repository, create_repo
from huggingface_hub import HfApi
from tqdm import tqdm
import transformers
@@ -429,9 +429,8 @@ def main():
if repo_name is None:
repo_name = Path(training_args.output_dir).absolute().name
# Create repo and retrieve repo_id
repo_id = create_repo(repo_name, exist_ok=True, token=training_args.hub_token).repo_id
# Clone repo locally
repo = Repository(training_args.output_dir, clone_from=repo_id, token=training_args.hub_token)
api = HfApi()
repo_id = api.create_repo(repo_name, exist_ok=True, token=training_args.hub_token).repo_id
# Get the datasets: you can either provide your own CSV/JSON/TXT training and evaluation files (see below)
# or just provide the name of one of the public datasets for token classification task available on the hub at https://huggingface.co/datasets/
@@ -798,7 +797,13 @@ def main():
model.save_pretrained(training_args.output_dir, params=params)
tokenizer.save_pretrained(training_args.output_dir)
if training_args.push_to_hub:
repo.push_to_hub(commit_message=f"Saving weights and logs of step {cur_step}", blocking=False)
api.upload_folder(
commit_message=f"Saving weights and logs of step {cur_step}",
folder_path=training_args.output_dir,
repo_id=repo_id,
repo_type="model",
token=training_args.hub_token,
)
epochs.desc = f"Epoch ... {epoch + 1}/{num_epochs}"
# Eval after training