>>> from huggingface_hub import HfApi
>>> api = HfApi()
>>> api.upload_file(
...     path_or_fileobj="/path/to/local/folder/README.md",
...     path_in_repo="README.md",
...     repo_id="username/test-dataset",
...     repo_type="dataset",
... )

>>> from huggingface_hub import HfApi
>>> api = HfApi()

# Upload all the content from the local folder to your remote Space.
# By default, files are uploaded at the root of the repo
>>> api.upload_folder(
...     folder_path="/path/to/local/space",
...     repo_id="username/my-cool-space",
...     repo_type="space",
... )

>>> api.upload_folder(
...     folder_path="/path/to/local/folder",
...     path_in_repo="my-dataset/train", # Upload to a specific folder
...     repo_id="username/test-dataset",
...     repo_type="dataset",
...     ignore_patterns="**/logs/*.txt", # Ignore all text logs
... )

>>> api.upload_folder(
...     folder_path="/path/to/local/folder/logs",
...     repo_id="username/trained-model",
...     path_in_repo="experiment/logs/",
...     allow_patterns="*.txt", # Upload all local text files
...     delete_patterns="*.txt", # Delete all remote text files before
... )

# Usage:  hf upload [repo_id] [local_path] [path_in_repo]
>>> hf upload Wauplin/my-cool-model ./models/model.safetensors model.safetensors
https://huggingface.co/Wauplin/my-cool-model/blob/main/model.safetensors

>>> hf upload Wauplin/my-cool-model ./models .
https://huggingface.co/Wauplin/my-cool-model/tree/main

>>> api.upload_large_folder(
...     repo_id="HuggingFaceM4/Docmatix",
...     repo_type="dataset",
...     folder_path="/path/to/local/docmatix",
... )

Repo created: https://huggingface.co/datasets/HuggingFaceM4/Docmatix
Found 5 candidate files to upload
Recovering from metadata files: 100%|█████████████████████████████████████| 5/5 [00:00<00:00, 542.66it/s]

---------- 2024-07-22 17:23:17 (0:00:00) ----------
Files:   hashed 5/5 (5.0G/5.0G) | pre-uploaded: 0/5 (0.0/5.0G) | committed: 0/5 (0.0/5.0G) | ignored: 0
Workers: hashing: 0 | get upload mode: 0 | pre-uploading: 5 | committing: 0 | waiting: 11
---------------------------------------------------

hf upload-large-folder HuggingFaceM4/Docmatix --repo-type=dataset /path/to/local/docmatix --num-workers=16

pip install -U "huggingface_hub"

>>> from huggingface_hub import HfApi
>>> api = HfApi()
>>> future = api.upload_folder( # Upload in the background (non-blocking action)
...     repo_id="username/my-model",
...     folder_path="checkpoints-001",
...     run_as_future=True,
... )
>>> future
Future(...)
>>> future.done()
False
>>> future.result() # Wait for the upload to complete (blocking action)
...

>>> from huggingface_hub import HfApi
>>> api = HfApi()
>>> api.run_as_future(api.create_repo, "username/my-model", exists_ok=True)
Future(...)
>>> api.upload_file(
...     repo_id="username/my-model",
...     path_in_repo="file.txt",
...     path_or_fileobj=b"file content",
...     run_as_future=True,
... )
Future(...)

>>> import json
>>> import uuid
>>> from pathlib import Path
>>> import gradio as gr
>>> from huggingface_hub import CommitScheduler

# Define the file where to save the data. Use UUID to make sure not to overwrite existing data from a previous run.
>>> feedback_file = Path("user_feedback/") / f"data_{uuid.uuid4()}.json"
>>> feedback_folder = feedback_file.parent

# Schedule regular uploads. Remote repo and local folder are created if they don't already exist.
>>> scheduler = CommitScheduler(
...     repo_id="report-translation-feedback",
...     repo_type="dataset",
...     folder_path=feedback_folder,
...     path_in_repo="data",
...     every=10,
... )

# Define the function that will be called when the user submits its feedback (to be called in Gradio)
>>> def save_feedback(input_text:str, output_1: str, output_2:str, user_choice: int) -> None:
...     """
...     Append input/outputs and user feedback to a JSON Lines file using a thread lock to avoid concurrent writes from different users.
...     """
...     with scheduler.lock:
...         with feedback_file.open("a") as f:
...             f.write(json.dumps({"input": input_text, "output_1": output_1, "output_2": output_2, "user_choice": user_choice}))
...             f.write("\n")

# Start Gradio
>>> with gr.Blocks() as demo:
>>>     ... # define Gradio demo + use `save_feedback`
>>> demo.launch()

class ZipScheduler(CommitScheduler):
    def push_to_hub(self):
        # 1. List PNG files
          png_files = list(self.folder_path.glob("*.png"))
          if len(png_files) == 0:
              return None  # return early if nothing to commit

        # 2. Zip png files in a single archive
        with tempfile.TemporaryDirectory() as tmpdir:
            archive_path = Path(tmpdir) / "train.zip"
            with zipfile.ZipFile(archive_path, "w", zipfile.ZIP_DEFLATED) as zip:
                for png_file in png_files:
                    zip.write(filename=png_file, arcname=png_file.name)

            # 3. Upload archive
            self.api.upload_file(..., path_or_fileobj=archive_path)

        # 4. Delete local png files to avoid re-uploading them later
        for png_file in png_files:
            png_file.unlink()

>>> from huggingface_hub import HfApi, CommitOperationAdd, CommitOperationDelete
>>> api = HfApi()
>>> operations = [
...     CommitOperationAdd(path_in_repo="LICENSE.md", path_or_fileobj="~/repo/LICENSE.md"),
...     CommitOperationAdd(path_in_repo="weights.h5", path_or_fileobj="~/repo/weights-final.h5"),
...     CommitOperationDelete(path_in_repo="old-weights.h5"),
...     CommitOperationDelete(path_in_repo="logs/"),
...     CommitOperationCopy(src_path_in_repo="image.png", path_in_repo="duplicate_image.png"),
... ]

>>> api.create_commit(
...     repo_id="lysandre/test-model",
...     operations=operations,
...     commit_message="Upload my model weights and license",
... )

>>> from huggingface_hub import CommitOperationAdd, preupload_lfs_files, create_commit, create_repo

>>> repo_id = create_repo("test_preupload").repo_id

>>> operations = [] # List of all `CommitOperationAdd` objects that will be generated
>>> for i in range(5):
...     content = ... # generate binary content
...     addition = CommitOperationAdd(path_in_repo=f"shard_{i}_of_5.bin", path_or_fileobj=content)
...     preupload_lfs_files(repo_id, additions=[addition])
...     operations.append(addition)

>>> # Create commit
>>> create_commit(repo_id, operations=operations, commit_message="Commit all shards")

hf lfs-enable-largefiles

>>> from huggingface_hub import Repository
>>> with Repository(local_dir="text-files", clone_from="<user>/text-files").commit(commit_message="My first file :)"):
...     with open("file.txt", "w+") as f:
...         f.write(json.dumps({"hey": 8}))

>>> import torch
>>> model = torch.nn.Transformer()
>>> with Repository("torch-model", clone_from="<user>/torch-model", token=True).commit(commit_message="My cool model :)"):
...     torch.save(model.state_dict(), "model.pt")

>>> with repo.commit(commit_message="My cool model :)", blocking=False)

>>> last_command = repo.command_queue[-1]
>>> last_command.status

# Inspect an error.
>>> last_command.stderr

# Check whether a push is completed or ongoing.
>>> last_command.is_done

# Check whether a push command has errored.
>>> last_command.failed

>>> from huggingface_hub import Repository
>>> repo = Repository(local_dir="path/to/local/repo")

>>> repo.git_pull()
>>> repo.push_to_hub(commit_message="Commit my-awesome-file to the Hub")

>>> repo.git_add("path/to/file")
>>> repo.git_commit(commit_message="add my first model config file :)")

>>> repo.git_push()