Replace all example usage of deprecated Repository

examples/flax/image-captioning/run_image_captioning_flax.py

@@ -36,14 +36,14 @@
 import nltk  # Here to have a nice missing dependency error message early on
 import numpy as np
 import optax
+from PIL import Image
 from datasets import Dataset, load_dataset
 from filelock import FileLock
 from flax import jax_utils, traverse_util
 from flax.jax_utils import unreplicate
 from flax.training import train_state
 from flax.training.common_utils import get_metrics, onehot, shard, shard_prng_key
-from huggingface_hub import Repository, create_repo
-from PIL import Image
+from huggingface_hub import HfApi
 from tqdm import tqdm
 
 import transformers
@@ -455,9 +455,8 @@ 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=args.hub_token).repo_id
 
     # Get the datasets: you can either provide your own CSV/JSON training and evaluation files (see below)
     # or just provide the name of one of the public datasets available on the hub at https://huggingface.co/datasets/
@@ -1052,7 +1051,7 @@ def generate_step(params, batch):
     if not os.path.isdir(os.path.join(training_args.output_dir)):
         os.makedirs(os.path.join(training_args.output_dir), exist_ok=True)
 
-    def save_ckpt(ckpt_dir: str, commit_msg: str = ""):
+    def save_ckpt(ckpt_dir: str, commit_msg: str):
         """save checkpoints and push to Hugging Face Hub if specified"""
 
         # save checkpoint after each epoch and push checkpoint to the hub
@@ -1061,7 +1060,13 @@ def save_ckpt(ckpt_dir: str, commit_msg: str = ""):
             model.save_pretrained(os.path.join(training_args.output_dir, ckpt_dir), params=params)
             tokenizer.save_pretrained(os.path.join(training_args.output_dir, ckpt_dir))
             if training_args.push_to_hub:
-                repo.push_to_hub(commit_message=commit_msg, blocking=False)
+                api.upload_folder(
+                    commit_message=commit_msg,
+                    folder_path=training_args.output_dir,
+                    repo_id=repo_id,
+                    repo_type="model",
+                    token=training_args.hub_token,
+                )
 
     def evaluation_loop(
         rng: jax.random.PRNGKey,

examples/flax/language-modeling/run_bart_dlm_flax.py

@@ -44,7 +44,7 @@
 from flax.jax_utils import pad_shard_unpad
 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
 
 from transformers import (
@@ -517,9 +517,8 @@ 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 available on the hub at https://huggingface.co/datasets/
@@ -949,7 +948,13 @@ def eval_step(params, batch):
                     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,
+                        )
 
     # Eval after training
     if training_args.do_eval:

examples/flax/language-modeling/run_clm_flax.py

@@ -44,7 +44,7 @@
 from flax.jax_utils import pad_shard_unpad, unreplicate
 from flax.training import train_state
 from flax.training.common_utils import get_metrics, onehot, shard, shard_prng_key
-from huggingface_hub import Repository, create_repo
+from huggingface_hub import HfApi
 from tqdm import tqdm
 
 import transformers
@@ -403,9 +403,8 @@ 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 available on the hub at https://huggingface.co/datasets/
@@ -847,8 +846,13 @@ def eval_step(params, batch):
                     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,
+                        )
     # Eval after training
     if training_args.do_eval:
         eval_metrics = []

examples/flax/language-modeling/run_mlm_flax.py

@@ -45,7 +45,7 @@
 from flax.jax_utils import pad_shard_unpad
 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
 
 from transformers import (
@@ -441,9 +441,8 @@ 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 available on the hub at https://huggingface.co/datasets/
@@ -890,8 +889,13 @@ def eval_step(params, batch):
                     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,
+                        )
     # Eval after training
     if training_args.do_eval:
         num_eval_samples = len(tokenized_datasets["validation"])

examples/flax/language-modeling/run_t5_mlm_flax.py

@@ -44,7 +44,7 @@
 from flax.jax_utils import pad_shard_unpad
 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
 
 from transformers import (
@@ -558,9 +558,8 @@ 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 available on the hub at https://huggingface.co/datasets/
@@ -977,8 +976,13 @@ def eval_step(params, batch):
                     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,
+                        )
     # Eval after training
     if training_args.do_eval:
         num_eval_samples = len(tokenized_datasets["validation"])

examples/flax/question-answering/run_qa.py

@@ -42,7 +42,7 @@
 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
 from utils_qa import postprocess_qa_predictions
 
@@ -493,9 +493,8 @@ 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
 
     # region Load Data
     # Get the datasets: you can either provide your own CSV/JSON/TXT training and evaluation files (see below)
@@ -1051,7 +1050,13 @@ def eval_step(state, batch):
                     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}"
     # endregion
 

examples/flax/speech-recognition/run_flax_speech_recognition_seq2seq.py

@@ -39,7 +39,7 @@
 from flax.jax_utils import pad_shard_unpad, unreplicate
 from flax.training import train_state
 from flax.training.common_utils import get_metrics, onehot, shard, shard_prng_key
-from huggingface_hub import Repository, create_repo
+from huggingface_hub import HfApi
 from torch.utils.data import DataLoader
 from tqdm import tqdm
 
@@ -427,8 +427,9 @@ def main():
             )
         else:
             repo_name = training_args.hub_model_id
-        create_repo(repo_name, exist_ok=True, token=training_args.hub_token)
-        repo = Repository(training_args.output_dir, clone_from=repo_name, token=training_args.hub_token)
+        # Create repo and retrieve repo_id
+        api = HfApi()
+        repo_id = api.create_repo(repo_name, exist_ok=True, token=training_args.hub_token).repo_id
 
     # 3. Load dataset
     raw_datasets = DatasetDict()
@@ -852,7 +853,13 @@ def generate_step(params, batch):
             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 epoch {epoch}", blocking=False)
+                api.upload_folder(
+                    commit_message=f"Saving weights and logs of epoch {epoch}",
+                    folder_path=training_args.output_dir,
+                    repo_id=repo_id,
+                    repo_type="model",
+                    token=training_args.hub_token,
+                )
 
 
 if __name__ == "__main__":

examples/flax/summarization/run_summarization_flax.py

@@ -44,7 +44,7 @@
 from flax.jax_utils import pad_shard_unpad, unreplicate
 from flax.training import train_state
 from flax.training.common_utils import get_metrics, onehot, shard, shard_prng_key
-from huggingface_hub import Repository, create_repo
+from huggingface_hub import HfApi
 from tqdm import tqdm
 
 import transformers
@@ -483,9 +483,8 @@ 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 training and evaluation files (see below)
     # or just provide the name of one of the public datasets available on the hub at https://huggingface.co/datasets/
@@ -976,7 +975,13 @@ def generate_step(params, batch):
             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 epoch {epoch}", blocking=False)
+                api.upload_folder(
+                    commit_message=f"Saving weights and logs of epoch {epoch}",
+                    folder_path=training_args.output_dir,
+                    repo_id=repo_id,
+                    repo_type="model",
+                    token=training_args.hub_token,
+                )
 
     # ======================== Prediction loop ==============================
     if training_args.do_predict:

examples/flax/text-classification/run_flax_glue.py

@@ -37,7 +37,7 @@
 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
@@ -373,9 +373,8 @@ 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 training and evaluation files (see below)
     # or specify a GLUE benchmark task (the dataset will be downloaded automatically from the datasets Hub).
@@ -677,7 +676,13 @@ def eval_step(state, batch):
                     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 epoch {epoch}",
+                            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}"
 
     # save the eval metrics in json

examples/flax/token-classification/run_flax_ner.py

@@ -39,7 +39,7 @@
 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 compute_metrics():
                     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