huggingface-hub 1.0.0rc5__py3-none-any.whl → 1.0.0rc7__py3-none-any.whl

huggingface_hub/cli/download.py

@@ -134,7 +134,7 @@ def download(
                 force_download=force_download,
                 token=token,
                 local_dir=local_dir,
-                library_name="hf",
+                library_name="huggingface-cli",
                 dry_run=dry_run,
             )
 
@@ -156,7 +156,7 @@ def download(
             cache_dir=cache_dir,
             token=token,
             local_dir=local_dir,
-            library_name="hf",
+            library_name="huggingface-cli",
             max_workers=max_workers,
             dry_run=dry_run,
         )

huggingface_hub/cli/repo.py

@@ -147,12 +147,6 @@ def repo_settings(
             help="Whether the repository should be private.",
         ),
     ] = None,
-    xet_enabled: Annotated[
-        Optional[bool],
-        typer.Option(
-            help=" Whether the repository should be enabled for Xet Storage.",
-        ),
-    ] = None,
     token: TokenOpt = None,
     repo_type: RepoTypeOpt = RepoType.model,
 ) -> None:
@@ -161,7 +155,6 @@ def repo_settings(
         repo_id=repo_id,
         gated=(gated.value if gated else None),  # type: ignore [arg-type]
         private=private,
-        xet_enabled=xet_enabled,
         repo_type=repo_type.value,
     )
     print(f"Successfully updated the settings of {ANSI.bold(repo_id)} on the Hub.")

huggingface_hub/cli/upload.py

@@ -55,10 +55,8 @@ import typer
 
 from huggingface_hub import logging
 from huggingface_hub._commit_scheduler import CommitScheduler
-from huggingface_hub.constants import HF_HUB_ENABLE_HF_TRANSFER
 from huggingface_hub.errors import RevisionNotFoundError
 from huggingface_hub.utils import disable_progress_bars, enable_progress_bars
-from huggingface_hub.utils._runtime import is_xet_available
 
 from ._cli_utils import PrivateOpt, RepoIdArg, RepoType, RepoTypeOpt, RevisionOpt, TokenOpt, get_hf_api
 
@@ -156,12 +154,6 @@ def upload(
             if delete is not None and len(delete) > 0:
                 warnings.warn("Ignoring --delete since a single file is uploaded.")
 
-        if not is_xet_available() and not HF_HUB_ENABLE_HF_TRANSFER:
-            logger.info(
-                "Consider using `hf_transfer` for faster uploads. This solution comes with some limitations. See"
-                " https://huggingface.co/docs/huggingface_hub/hf_transfer for more details."
-            )
-
         # Schedule commits if `every` is set
         if every is not None:
             if os.path.isfile(resolved_local_path):

huggingface_hub/community.py

@@ -7,7 +7,7 @@ for more information on Pull Requests, Discussions, and the community tab.
 
 from dataclasses import dataclass
 from datetime import datetime
-from typing import Literal, Optional, Union
+from typing import Literal, Optional, TypedDict, Union
 
 from . import constants
 from .utils import parse_datetime
@@ -143,6 +143,14 @@ class DiscussionWithDetails(Discussion):
     diff: Optional[str]
 
 
+class DiscussionEventArgs(TypedDict):
+    id: str
+    type: str
+    created_at: datetime
+    author: str
+    _event: dict
+
+
 @dataclass
 class DiscussionEvent:
     """
@@ -319,13 +327,13 @@ def deserialize_event(event: dict) -> DiscussionEvent:
     event_type: str = event["type"]
     created_at = parse_datetime(event["createdAt"])
 
-    common_args = dict(
-        id=event_id,
-        type=event_type,
-        created_at=created_at,
-        author=event.get("author", {}).get("name", "deleted"),
-        _event=event,
-    )
+    common_args: DiscussionEventArgs = {
+        "id": event_id,
+        "type": event_type,
+        "created_at": created_at,
+        "author": event.get("author", {}).get("name", "deleted"),
+        "_event": event,
+    }
 
     if event_type == "comment":
         return DiscussionComment(

huggingface_hub/constants.py

@@ -35,7 +35,6 @@ DEFAULT_ETAG_TIMEOUT = 10
 DEFAULT_DOWNLOAD_TIMEOUT = 10
 DEFAULT_REQUEST_TIMEOUT = 10
 DOWNLOAD_CHUNK_SIZE = 10 * 1024 * 1024
-HF_TRANSFER_CONCURRENCY = 100
 MAX_HTTP_DOWNLOAD_SIZE = 50 * 1000 * 1000 * 1000  # 50 GB
 
 # Constants for serialization
@@ -215,18 +214,18 @@ HF_HUB_DISABLE_EXPERIMENTAL_WARNING: bool = _is_true(os.environ.get("HF_HUB_DISA
 # Disable sending the cached token by default is all HTTP requests to the Hub
 HF_HUB_DISABLE_IMPLICIT_TOKEN: bool = _is_true(os.environ.get("HF_HUB_DISABLE_IMPLICIT_TOKEN"))
 
-# Enable fast-download using external dependency "hf_transfer"
-# See:
-# - https://pypi.org/project/hf-transfer/
-# - https://github.com/huggingface/hf_transfer (private)
-HF_HUB_ENABLE_HF_TRANSFER: bool = _is_true(os.environ.get("HF_HUB_ENABLE_HF_TRANSFER"))
+HF_XET_HIGH_PERFORMANCE: bool = _is_true(os.environ.get("HF_XET_HIGH_PERFORMANCE"))
 
+# hf_transfer is not used anymore. Let's warn user is case they set the env variable
+if _is_true(os.environ.get("HF_HUB_ENABLE_HF_TRANSFER")) and not HF_XET_HIGH_PERFORMANCE:
+    import warnings
 
-# UNUSED
-# We don't use symlinks in local dir anymore.
-HF_HUB_LOCAL_DIR_AUTO_SYMLINK_THRESHOLD: int = (
-    _as_int(os.environ.get("HF_HUB_LOCAL_DIR_AUTO_SYMLINK_THRESHOLD")) or 5 * 1024 * 1024
-)
+    warnings.warn(
+        "The `HF_HUB_ENABLE_HF_TRANSFER` environment variable is deprecated as 'hf_transfer' is not used anymore. "
+        "Please use `HF_XET_HIGH_PERFORMANCE` instead to enable high performance transfer with Xet. "
+        "Visit https://huggingface.co/docs/huggingface_hub/package_reference/environment_variables#hfxethighperformance for more details.",
+        DeprecationWarning,
+    )
 
 # Used to override the etag timeout on a system level
 HF_HUB_ETAG_TIMEOUT: int = _as_int(os.environ.get("HF_HUB_ETAG_TIMEOUT")) or DEFAULT_ETAG_TIMEOUT

huggingface_hub/file_download.py

@@ -379,38 +379,16 @@ def http_get(
         # If the file is already fully downloaded, we don't need to download it again.
         return
 
-    has_custom_range_header = headers is not None and any(h.lower() == "range" for h in headers)
-    hf_transfer = None
-    if constants.HF_HUB_ENABLE_HF_TRANSFER:
-        if resume_size != 0:
-            warnings.warn("'hf_transfer' does not support `resume_size`: falling back to regular download method")
-        elif has_custom_range_header:
-            warnings.warn("'hf_transfer' ignores custom 'Range' headers; falling back to regular download method")
-        else:
-            try:
-                import hf_transfer  # type: ignore[no-redef]
-            except ImportError:
-                raise ValueError(
-                    "Fast download using 'hf_transfer' is enabled"
-                    " (HF_HUB_ENABLE_HF_TRANSFER=1) but 'hf_transfer' package is not"
-                    " available in your environment. Try `pip install hf_transfer`."
-                )
-
     initial_headers = headers
     headers = copy.deepcopy(headers) or {}
     if resume_size > 0:
         headers["Range"] = _adjust_range_header(headers.get("Range"), resume_size)
     elif expected_size and expected_size > constants.MAX_HTTP_DOWNLOAD_SIZE:
-        # Any files over 50GB will not be available through basic http request.
-        # Setting the range header to 0-0 will force the server to return the file size in the Content-Range header.
-        # Since hf_transfer splits the download into chunks, the process will succeed afterwards.
-        if hf_transfer:
-            headers["Range"] = "bytes=0-0"
-        else:
-            raise ValueError(
-                "The file is too large to be downloaded using the regular download method. Use `hf_transfer` or `hf_xet` instead."
-                " Try `pip install hf_transfer` or `pip install hf_xet`."
-            )
+        # Any files over 50GB will not be available through basic http requests.
+        raise ValueError(
+            "The file is too large to be downloaded using the regular download method. "
+            " Install `hf_xet` with `pip install hf_xet` for xet-powered downloads."
+        )
 
     with http_stream_backoff(
         method="GET",
@@ -451,31 +429,6 @@ def http_get(
         )
 
         with progress_cm as progress:
-            if hf_transfer and total is not None and total > 5 * constants.DOWNLOAD_CHUNK_SIZE:
-                try:
-                    hf_transfer.download(
-                        url=url,
-                        filename=temp_file.name,
-                        max_files=constants.HF_TRANSFER_CONCURRENCY,
-                        chunk_size=constants.DOWNLOAD_CHUNK_SIZE,
-                        headers=initial_headers,
-                        parallel_failures=3,
-                        max_retries=5,
-                        callback=progress.update,
-                    )
-                except Exception as e:
-                    raise RuntimeError(
-                        "An error occurred while downloading using `hf_transfer`. Consider"
-                        " disabling HF_HUB_ENABLE_HF_TRANSFER for better error handling."
-                    ) from e
-                if expected_size is not None and expected_size != os.path.getsize(temp_file.name):
-                    raise EnvironmentError(
-                        consistency_error_message.format(
-                            actual_size=os.path.getsize(temp_file.name),
-                        )
-                    )
-                return
-
             new_resume_size = resume_size
             try:
                 for chunk in response.iter_bytes(chunk_size=constants.DOWNLOAD_CHUNK_SIZE):
@@ -1780,7 +1733,7 @@ def _download_to_tmp_and_move(
     Internal logic:
     - return early if file is already downloaded
     - resume download if possible (from incomplete file)
-    - do not resume download if `force_download=True` or `HF_HUB_ENABLE_HF_TRANSFER=True`
+    - do not resume download if `force_download=True`
     - check disk space before downloading
     - download content to a temporary file
     - set correct permissions on temporary file
@@ -1792,16 +1745,11 @@ def _download_to_tmp_and_move(
         # Do nothing if already exists (except if force_download=True)
         return
 
-    if incomplete_path.exists() and (force_download or constants.HF_HUB_ENABLE_HF_TRANSFER):
+    if incomplete_path.exists() and force_download:
         # By default, we will try to resume the download if possible.
-        # However, if the user has set `force_download=True` or if `hf_transfer` is enabled, then we should
+        # However, if the user has set `force_download=True`, then we should
         # not resume the download => delete the incomplete file.
-        message = f"Removing incomplete file '{incomplete_path}'"
-        if force_download:
-            message += " (force_download=True)"
-        elif constants.HF_HUB_ENABLE_HF_TRANSFER:
-            message += " (hf_transfer=True)"
-        logger.info(message)
+        logger.info(f"Removing incomplete file '{incomplete_path}' (force_download=True)")
         incomplete_path.unlink(missing_ok=True)
 
     with incomplete_path.open("ab") as f: