huggingface-hub 0.12.0rc0__py3-none-any.whl → 0.13.0rc0__py3-none-any.whl

huggingface_hub/_snapshot_download.py

@@ -13,9 +13,9 @@ from .constants import (
 )
 from .file_download import REGEX_COMMIT_HASH, hf_hub_download, repo_folder_name
 from .hf_api import HfApi
-from .utils import filter_repo_objects, logging
+from .utils import filter_repo_objects, logging, validate_hf_hub_args
 from .utils import tqdm as hf_tqdm
-from .utils import validate_hf_hub_args
+from .utils._typing import Literal
 
 
 logger = logging.get_logger(__name__)
@@ -28,6 +28,8 @@ def snapshot_download(
     revision: Optional[str] = None,
     repo_type: Optional[str] = None,
     cache_dir: Union[str, Path, None] = None,
+    local_dir: Union[str, Path, None] = None,
+    local_dir_use_symlinks: Union[bool, Literal["auto"]] = "auto",
     library_name: Optional[str] = None,
     library_version: Optional[str] = None,
     user_agent: Optional[Union[Dict, str]] = None,
@@ -41,15 +43,30 @@ def snapshot_download(
     max_workers: int = 8,
     tqdm_class: Optional[base_tqdm] = None,
 ) -> str:
-    """Download all files of a repo.
-
-    Downloads a whole snapshot of a repo's files at the specified revision. This
-    is useful when you want all files from a repo, because you don't know which
-    ones you will need a priori. All files are nested inside a folder in order
-    to keep their actual filename relative to that folder.
-
-    An alternative would be to just clone a repo but this would require that the
-    user always has git and git-lfs installed, and properly configured.
+    """Download repo files.
+
+    Download a whole snapshot of a repo's files at the specified revision. This is useful when you want all files from
+    a repo, because you don't know which ones you will need a priori. All files are nested inside a folder in order
+    to keep their actual filename relative to that folder. You can also filter which files to download using
+    `allow_patterns` and `ignore_patterns`.
+
+    If `local_dir` is provided, the file structure from the repo will be replicated in this location. You can configure
+    how you want to move those files:
+      - If `local_dir_use_symlinks="auto"` (default), files are downloaded and stored in the cache directory as blob
+        files. Small files (<5MB) are duplicated in `local_dir` while a symlink is created for bigger files. The goal
+        is to be able to manually edit and save small files without corrupting the cache while saving disk space for
+        binary files. The 5MB threshold can be configured with the `HF_HUB_LOCAL_DIR_AUTO_SYMLINK_THRESHOLD`
+        environment variable.
+      - If `local_dir_use_symlinks=True`, files are downloaded, stored in the cache directory and symlinked in `local_dir`.
+        This is optimal in term of disk usage but files must not be manually edited.
+      - If `local_dir_use_symlinks=False` and the blob files exist in the cache directory, they are duplicated in the
+        local dir. This means disk usage is not optimized.
+      - Finally, if `local_dir_use_symlinks=False` and the blob files do not exist in the cache directory, then the
+        files are downloaded and directly placed under `local_dir`. This means if you need to download them again later,
+        they will be re-downloaded entirely.
+
+    An alternative would be to clone the repo but this requires git and git-lfs to be installed and properly
+    configured. It is also not possible to filter which files to download when cloning a repository using git.
 
     Args:
         repo_id (`str`):
@@ -58,10 +75,18 @@ def snapshot_download(
             An optional Git revision id which can be a branch name, a tag, or a
             commit hash.
         repo_type (`str`, *optional*):
-            Set to `"dataset"` or `"space"` if uploading to a dataset or space,
-            `None` or `"model"` if uploading to a model. Default is `None`.
+            Set to `"dataset"` or `"space"` if downloading from a dataset or space,
+            `None` or `"model"` if downloading from a model. Default is `None`.
         cache_dir (`str`, `Path`, *optional*):
             Path to the folder where cached files are stored.
+        local_dir (`str` or `Path`, *optional*:
+            If provided, the downloaded files will be placed under this directory, either as symlinks (default) or
+            regular files (see description for more details).
+        local_dir_use_symlinks (`"auto"` or `bool`, defaults to `"auto"`):
+            To be used with `local_dir`. If set to "auto", the cache directory will be used and the file will be either
+            duplicated or symlinked to the local directory depending on its size. It set to `True`, a symlink will be
+            created, no matter the file size. If set to `False`, the file will either be duplicated from cache (if
+            already exists) or downloaded from the Hub and not cached. See description for more details.
         library_name (`str`, *optional*):
             The name of the library to which the object corresponds.
         library_version (`str`, *optional*):
@@ -124,14 +149,9 @@ def snapshot_download(
     if repo_type is None:
         repo_type = "model"
     if repo_type not in REPO_TYPES:
-        raise ValueError(
-            f"Invalid repo type: {repo_type}. Accepted repo types are:"
-            f" {str(REPO_TYPES)}"
-        )
+        raise ValueError(f"Invalid repo type: {repo_type}. Accepted repo types are: {str(REPO_TYPES)}")
 
-    storage_folder = os.path.join(
-        cache_dir, repo_folder_name(repo_id=repo_id, repo_type=repo_type)
-    )
+    storage_folder = os.path.join(cache_dir, repo_folder_name(repo_id=repo_id, repo_type=repo_type))
 
     # if we have no internet connection we will look for an
     # appropriate folder in the cache
@@ -166,9 +186,7 @@ def snapshot_download(
         revision=revision,
         token=token,
     )
-    assert (
-        repo_info.sha is not None
-    ), "Repo info returned from server must have a revision sha."
+    assert repo_info.sha is not None, "Repo info returned from server must have a revision sha."
     filtered_repo_files = list(
         filter_repo_objects(
             items=[f.rfilename for f in repo_info.siblings],
@@ -197,6 +215,8 @@ def snapshot_download(
             repo_type=repo_type,
             revision=commit_hash,
             cache_dir=cache_dir,
+            local_dir=local_dir,
+            local_dir_use_symlinks=local_dir_use_symlinks,
             library_name=library_name,
             library_version=library_version,
             user_agent=user_agent,
@@ -221,4 +241,6 @@ def snapshot_download(
             tqdm_class=tqdm_class or hf_tqdm,
         )
 
+    if local_dir is not None:
+        return str(os.path.realpath(local_dir))
     return snapshot_folder

huggingface_hub/_space_api.py

@@ -39,6 +39,7 @@ class SpaceStage(str, Enum):
     RUNTIME_ERROR = "RUNTIME_ERROR"
     DELETING = "DELETING"
     STOPPED = "STOPPED"
+    PAUSED = "PAUSED"
 
 
 class SpaceHardware(str, Enum):
@@ -86,3 +87,9 @@ class SpaceRuntime:
     hardware: Optional[SpaceHardware]
     requested_hardware: Optional[SpaceHardware]
     raw: Dict
+
+    def __init__(self, data: Dict) -> None:
+        self.stage = data["stage"]
+        self.hardware = data["hardware"]["current"]
+        self.requested_hardware = data["hardware"]["requested"]
+        self.raw = data

huggingface_hub/commands/delete_cache.py

@@ -78,6 +78,7 @@ except ImportError:
 
 def require_inquirer_py(fn: Callable) -> Callable:
     """Decorator to flag methods that require `InquirerPy`."""
+
     # TODO: refactor this + imports in a unified pattern across codebase
     @wraps(fn)
     def _inner(*args, **kwargs):
@@ -100,17 +101,13 @@ _CANCEL_DELETION_STR = "CANCEL_DELETION"
 class DeleteCacheCommand(BaseHuggingfaceCLICommand):
     @staticmethod
     def register_subcommand(parser: _SubParsersAction):
-        delete_cache_parser = parser.add_parser(
-            "delete-cache", help="Delete revisions from the cache directory."
-        )
+        delete_cache_parser = parser.add_parser("delete-cache", help="Delete revisions from the cache directory.")
 
         delete_cache_parser.add_argument(
             "--dir",
             type=str,
             default=None,
-            help=(
-                "cache directory (optional). Default to the default HuggingFace cache."
-            ),
+            help="cache directory (optional). Default to the default HuggingFace cache.",
         )
 
         delete_cache_parser.add_argument(
@@ -141,10 +138,7 @@ class DeleteCacheCommand(BaseHuggingfaceCLICommand):
 
         # If deletion is not cancelled
         if len(selected_hashes) > 0 and _CANCEL_DELETION_STR not in selected_hashes:
-            confirm_message = (
-                _get_expectations_str(hf_cache_info, selected_hashes)
-                + " Confirm deletion ?"
-            )
+            confirm_message = _get_expectations_str(hf_cache_info, selected_hashes) + " Confirm deletion ?"
 
             # Confirm deletion
             if self.disable_tui:
@@ -175,9 +169,7 @@ def _manual_review_tui(hf_cache_info: HFCacheInfo, preselected: List[str]) -> Li
     Displays a multi-select menu in the terminal (TUI).
     """
     # Define multiselect list
-    choices = _get_tui_choices_from_scan(
-        repos=hf_cache_info.repos, preselected=preselected
-    )
+    choices = _get_tui_choices_from_scan(repos=hf_cache_info.repos, preselected=preselected)
     checkbox = inquirer.checkbox(
         message="Select revisions to delete:",
         choices=choices,  # List of revisions with some pre-selection
@@ -187,15 +179,10 @@ def _manual_review_tui(hf_cache_info: HFCacheInfo, preselected: List[str]) -> Li
         # deletion.
         instruction=_get_expectations_str(
             hf_cache_info,
-            selected_hashes=[
-                c.value for c in choices if isinstance(c, Choice) and c.enabled
-            ],
+            selected_hashes=[c.value for c in choices if isinstance(c, Choice) and c.enabled],
         ),
         # We use the long instruction to should keybindings instructions to the user
-        long_instruction=(
-            "Press <space> to select, <enter> to validate and <ctrl+c> to quit"
-            " without modification."
-        ),
+        long_instruction="Press <space> to select, <enter> to validate and <ctrl+c> to quit without modification.",
         # Message that is displayed once the user validates its selection.
         transformer=lambda result: f"{len(result)} revision(s) selected.",
     )
@@ -207,11 +194,7 @@ def _manual_review_tui(hf_cache_info: HFCacheInfo, preselected: List[str]) -> Li
         # a revision hash is selected/unselected.
         checkbox._instruction = _get_expectations_str(
             hf_cache_info,
-            selected_hashes=[
-                choice["value"]
-                for choice in checkbox.content_control.choices
-                if choice["enabled"]
-            ],
+            selected_hashes=[choice["value"] for choice in checkbox.content_control.choices if choice["enabled"]],
         )
 
     checkbox.kb_func_lookup["toggle"].append({"func": _update_expectations})
@@ -229,9 +212,7 @@ def _ask_for_confirmation_tui(message: str, default: bool = True) -> bool:
     return inquirer.confirm(message, default=default).execute()
 
 
-def _get_tui_choices_from_scan(
-    repos: Iterable[CachedRepoInfo], preselected: List[str]
-) -> List:
+def _get_tui_choices_from_scan(repos: Iterable[CachedRepoInfo], preselected: List[str]) -> List:
     """Build a list of choices from the scanned repos.
 
     Args:
@@ -282,9 +263,7 @@ def _get_tui_choices_from_scan(
     return choices
 
 
-def _manual_review_no_tui(
-    hf_cache_info: HFCacheInfo, preselected: List[str]
-) -> List[str]:
+def _manual_review_no_tui(hf_cache_info: HFCacheInfo, preselected: List[str]) -> List[str]:
     """Ask the user for a manual review of the revisions to delete.
 
     Used when TUI is disabled. Manual review happens in a separate tmp file that the
@@ -317,7 +296,7 @@ def _manual_review_no_tui(
 
     # 2. Prompt instructions to user.
     instructions = f"""
-    TUI is disabled. In other to select which revisions you want to delete, please edit
+    TUI is disabled. In order to select which revisions you want to delete, please edit
     the following file using the text editor of your choice. Instructions for manual
     editing are located at the beginning of the file. Edit the file, save it and confirm
     to continue.
@@ -357,9 +336,7 @@ def _ask_for_confirmation_no_tui(message: str, default: bool = True) -> bool:
         print(f"Invalid input. Must be one of {ALL}")
 
 
-def _get_expectations_str(
-    hf_cache_info: HFCacheInfo, selected_hashes: List[str]
-) -> str:
+def _get_expectations_str(hf_cache_info: HFCacheInfo, selected_hashes: List[str]) -> str:
     """Format a string to display to the user how much space would be saved.
 
     Example:
@@ -371,10 +348,7 @@ def _get_expectations_str(
     if _CANCEL_DELETION_STR in selected_hashes:
         return "Nothing will be deleted."
     strategy = hf_cache_info.delete_revisions(*selected_hashes)
-    return (
-        f"{len(selected_hashes)} revisions selected counting for"
-        f" {strategy.expected_freed_size_str}."
-    )
+    return f"{len(selected_hashes)} revisions selected counting for {strategy.expected_freed_size_str}."
 
 
 def _read_manual_review_tmp_file(tmp_path: str) -> List[str]:

huggingface_hub/commands/env.py

@@ -28,9 +28,7 @@ class EnvironmentCommand(BaseHuggingfaceCLICommand):
 
     @staticmethod
     def register_subcommand(parser: _SubParsersAction):
-        env_parser = parser.add_parser(
-            "env", help="Print information about the environment."
-        )
+        env_parser = parser.add_parser("env", help="Print information about the environment.")
         env_parser.set_defaults(func=EnvironmentCommand)
 
     def run(self) -> None:

huggingface_hub/commands/huggingface_cli.py

@@ -23,9 +23,7 @@ from huggingface_hub.commands.user import UserCommands
 
 
 def main():
-    parser = ArgumentParser(
-        "huggingface-cli", usage="huggingface-cli <command> [<args>]"
-    )
+    parser = ArgumentParser("huggingface-cli", usage="huggingface-cli <command> [<args>]")
     commands_parser = parser.add_subparsers(help="huggingface-cli command helpers")
 
     # Register commands

huggingface_hub/commands/lfs.py

@@ -24,6 +24,7 @@ from argparse import _SubParsersAction
 from typing import Dict, List, Optional
 
 import requests
+
 from huggingface_hub.commands import BaseHuggingfaceCLICommand
 from huggingface_hub.lfs import LFS_MULTIPART_UPLOAD_COMMAND, SliceFileObj
 
@@ -60,9 +61,7 @@ class LfsCommands(BaseHuggingfaceCLICommand):
             "lfs-enable-largefiles",
             help="Configure your repository to enable upload of files > 5GB.",
         )
-        enable_parser.add_argument(
-            "path", type=str, help="Local path to repository you want to configure."
-        )
+        enable_parser.add_argument("path", type=str, help="Local path to repository you want to configure.")
         enable_parser.set_defaults(func=lambda args: LfsEnableCommand(args))
 
         upload_parser = parser.add_parser(
@@ -87,8 +86,7 @@ class LfsEnableCommand:
             cwd=local_path,
         )
         subprocess.run(
-            "git config lfs.customtransfer.multipart.args"
-            f" {LFS_MULTIPART_UPLOAD_COMMAND}".split(),
+            f"git config lfs.customtransfer.multipart.args {LFS_MULTIPART_UPLOAD_COMMAND}".split(),
             check=True,
             cwd=local_path,
         )
@@ -126,9 +124,7 @@ class LfsUploadCommand:
         # sends initiation data to the process over stdin.
         # This tells the process useful information about the configuration.
         init_msg = json.loads(sys.stdin.readline().strip())
-        if not (
-            init_msg.get("event") == "init" and init_msg.get("operation") == "upload"
-        ):
+        if not (init_msg.get("event") == "init" and init_msg.get("operation") == "upload"):
             write_msg({"error": {"code": 32, "message": "Wrong lfs init operation"}})
             sys.exit(1)
 

huggingface_hub/commands/scan_cache.py

@@ -32,18 +32,13 @@ from ._cli_utils import ANSI, tabulate
 class ScanCacheCommand(BaseHuggingfaceCLICommand):
     @staticmethod
     def register_subcommand(parser: _SubParsersAction):
-        scan_cache_parser = parser.add_parser(
-            "scan-cache", help="Scan cache directory."
-        )
+        scan_cache_parser = parser.add_parser("scan-cache", help="Scan cache directory.")
 
         scan_cache_parser.add_argument(
             "--dir",
             type=str,
             default=None,
-            help=(
-                "cache directory to scan (optional). Default to the"
-                " default HuggingFace cache."
-            ),
+            help="cache directory to scan (optional). Default to the default HuggingFace cache.",
         )
         scan_cache_parser.add_argument(
             "-v",
@@ -98,9 +93,7 @@ class ScanCacheCommand(BaseHuggingfaceCLICommand):
                             ", ".join(sorted(repo.refs)),
                             str(repo.repo_path),
                         ]
-                        for repo in sorted(
-                            hf_cache_info.repos, key=lambda repo: repo.repo_path
-                        )
+                        for repo in sorted(hf_cache_info.repos, key=lambda repo: repo.repo_path)
                     ],
                     headers=[
                         "REPO ID",
@@ -128,12 +121,8 @@ class ScanCacheCommand(BaseHuggingfaceCLICommand):
                             ", ".join(sorted(revision.refs)),
                             str(revision.snapshot_path),
                         ]
-                        for repo in sorted(
-                            hf_cache_info.repos, key=lambda repo: repo.repo_path
-                        )
-                        for revision in sorted(
-                            repo.revisions, key=lambda revision: revision.commit_hash
-                        )
+                        for repo in sorted(hf_cache_info.repos, key=lambda repo: repo.repo_path)
+                        for revision in sorted(repo.revisions, key=lambda revision: revision.commit_hash)
                     ],
                     headers=[
                         "REPO ID",

huggingface_hub/commands/user.py

@@ -14,6 +14,8 @@
 import subprocess
 from argparse import _SubParsersAction
 
+from requests.exceptions import HTTPError
+
 from huggingface_hub.commands import BaseHuggingfaceCLICommand
 from huggingface_hub.constants import (
     ENDPOINT,
@@ -22,21 +24,18 @@ from huggingface_hub.constants import (
     SPACES_SDK_TYPES,
 )
 from huggingface_hub.hf_api import HfApi
-from requests.exceptions import HTTPError
 
-from .._login import (  # noqa: F401 # for backward compatibility
+from .._login import (  # noqa: F401 # for backward compatibility  # noqa: F401 # for backward compatibility
     NOTEBOOK_LOGIN_PASSWORD_HTML,
     NOTEBOOK_LOGIN_TOKEN_HTML_END,
     NOTEBOOK_LOGIN_TOKEN_HTML_START,
-)
-from .._login import (  # noqa: F401 # for backward compatibility
-    _currently_setup_credential_helpers as currently_setup_credential_helpers,
-)
-from .._login import (  # noqa: F401 # for backward compatibility
     login,
     logout,
     notebook_login,
 )
+from .._login import (
+    _currently_setup_credential_helpers as currently_setup_credential_helpers,  # noqa: F401 # for backward compatibility
+)
 from ..utils import HfFolder
 from ._cli_utils import ANSI
 
@@ -44,13 +43,19 @@ from ._cli_utils import ANSI
 class UserCommands(BaseHuggingfaceCLICommand):
     @staticmethod
     def register_subcommand(parser: _SubParsersAction):
-        login_parser = parser.add_parser(
-            "login", help="Log in using a token from huggingface.co/settings/tokens"
+        login_parser = parser.add_parser("login", help="Log in using a token from huggingface.co/settings/tokens")
+        login_parser.add_argument(
+            "--token",
+            type=str,
+            help="Token generated from https://huggingface.co/settings/tokens",
         )
-        login_parser.set_defaults(func=lambda args: LoginCommand(args))
-        whoami_parser = parser.add_parser(
-            "whoami", help="Find out which huggingface.co account you are logged in as."
+        login_parser.add_argument(
+            "--add-to-git-credential",
+            action="store_true",
+            help="Optional: Save token to git credential helper.",
         )
+        login_parser.set_defaults(func=lambda args: LoginCommand(args))
+        whoami_parser = parser.add_parser("whoami", help="Find out which huggingface.co account you are logged in as.")
         whoami_parser.set_defaults(func=lambda args: WhoamiCommand(args))
         logout_parser = parser.add_parser("logout", help="Log out")
         logout_parser.set_defaults(func=lambda args: LogoutCommand(args))
@@ -58,43 +63,25 @@ class UserCommands(BaseHuggingfaceCLICommand):
         # new system: git-based repo system
         repo_parser = parser.add_parser(
             "repo",
-            help=(
-                "{create, ls-files} Commands to interact with your huggingface.co"
-                " repos."
-            ),
-        )
-        repo_subparsers = repo_parser.add_subparsers(
-            help="huggingface.co repos related commands"
-        )
-        repo_create_parser = repo_subparsers.add_parser(
-            "create", help="Create a new repo on huggingface.co"
+            help="{create, ls-files} Commands to interact with your huggingface.co repos.",
         )
+        repo_subparsers = repo_parser.add_subparsers(help="huggingface.co repos related commands")
+        repo_create_parser = repo_subparsers.add_parser("create", help="Create a new repo on huggingface.co")
         repo_create_parser.add_argument(
             "name",
             type=str,
-            help=(
-                "Name for your repo. Will be namespaced under your username to build"
-                " the repo id."
-            ),
+            help="Name for your repo. Will be namespaced under your username to build the repo id.",
         )
         repo_create_parser.add_argument(
             "--type",
             type=str,
-            help=(
-                'Optional: repo_type: set to "dataset" or "space" if creating a dataset'
-                " or space, default is model."
-            ),
-        )
-        repo_create_parser.add_argument(
-            "--organization", type=str, help="Optional: organization namespace."
+            help='Optional: repo_type: set to "dataset" or "space" if creating a dataset or space, default is model.',
         )
+        repo_create_parser.add_argument("--organization", type=str, help="Optional: organization namespace.")
         repo_create_parser.add_argument(
             "--space_sdk",
             type=str,
-            help=(
-                "Optional: Hugging Face Spaces SDK type. Required when --type is set to"
-                ' "space".'
-            ),
+            help='Optional: Hugging Face Spaces SDK type. Required when --type is set to "space".',
             choices=SPACES_SDK_TYPES,
         )
         repo_create_parser.add_argument(
@@ -114,7 +101,7 @@ class BaseUserCommand:
 
 class LoginCommand(BaseUserCommand):
     def run(self):
-        login()
+        login(token=self.args.token, add_to_git_credential=self.args.add_to_git_credential)
 
 
 class LogoutCommand(BaseUserCommand):
@@ -169,9 +156,7 @@ class RepoCreateCommand(BaseUserCommand):
         print("")
 
         user = self._api.whoami(token)["name"]
-        namespace = (
-            self.args.organization if self.args.organization is not None else user
-        )
+        namespace = self.args.organization if self.args.organization is not None else user
 
         repo_id = f"{namespace}/{self.args.name}"
 
@@ -204,9 +189,6 @@ class RepoCreateCommand(BaseUserCommand):
             exit(1)
         print("\nYour repo now lives at:")
         print(f"  {ANSI.bold(url)}")
-        print(
-            "\nYou can clone it locally with the command below,"
-            " and commit/push as usual."
-        )
+        print("\nYou can clone it locally with the command below, and commit/push as usual.")
         print(f"\n  git clone {url}")
         print("")

huggingface_hub/community.py

@@ -44,7 +44,7 @@ class Discussion:
             The username of the Discussion / Pull Request author.
             Can be `"deleted"` if the user has been deleted since.
         is_pull_request (`bool`):
-            Wether or not this is a Pull Request.
+            Whether or not this is a Pull Request.
         created_at (`datetime`):
             The `datetime` of creation of the Discussion / Pull Request.
     """
@@ -96,7 +96,7 @@ class DiscussionWithDetails(Discussion):
             The username of the Discussion / Pull Request author.
             Can be `"deleted"` if the user has been deleted since.
         is_pull_request (`bool`):
-            Wether or not this is a Pull Request.
+            Whether or not this is a Pull Request.
         created_at (`datetime`):
             The `datetime` of creation of the Discussion / Pull Request.
         events (`list` of [`DiscussionEvent`])
@@ -175,7 +175,7 @@ class DiscussionComment(DiscussionEvent):
         content (`str`):
             The raw markdown content of the comment. Mentions, links and images are not rendered.
         edited (`bool`):
-            Wether or not this comment has been edited.
+            Whether or not this comment has been edited.
         hidden (`bool`):
             Whether or not this comment has been hidden.
     """
@@ -196,7 +196,7 @@ class DiscussionComment(DiscussionEvent):
 
     @property
     def last_edited_by(self) -> str:
-        """The last edit tiem, as a `datetime` object."""
+        """The last edit time, as a `datetime` object."""
         return self._event["data"]["latest"].get("author", {}).get("name", "deleted")
 
     @property

huggingface_hub/constants.py

@@ -15,10 +15,10 @@ def _is_true(value: Optional[str]) -> bool:
     return value.upper() in ENV_VARS_TRUE_VALUES
 
 
-def _is_true_or_auto(value: Optional[str]) -> bool:
+def _as_int(value: Optional[str]) -> Optional[int]:
     if value is None:
-        return False
-    return value.upper() in ENV_VARS_TRUE_AND_AUTO_VALUES
+        return None
+    return int(value)
 
 
 # Constants for file downloads
@@ -39,15 +39,15 @@ HUGGINGFACE_CO_URL_HOME = "https://huggingface.co/"
 
 _staging_mode = _is_true(os.environ.get("HUGGINGFACE_CO_STAGING"))
 
-ENDPOINT = os.getenv("HF_ENDPOINT") or (
-    "https://hub-ci.huggingface.co" if _staging_mode else "https://huggingface.co"
-)
+ENDPOINT = os.getenv("HF_ENDPOINT") or ("https://hub-ci.huggingface.co" if _staging_mode else "https://huggingface.co")
 
 HUGGINGFACE_CO_URL_TEMPLATE = ENDPOINT + "/{repo_id}/resolve/{revision}/{filename}"
 HUGGINGFACE_HEADER_X_REPO_COMMIT = "X-Repo-Commit"
 HUGGINGFACE_HEADER_X_LINKED_ETAG = "X-Linked-Etag"
 HUGGINGFACE_HEADER_X_LINKED_SIZE = "X-Linked-Size"
 
+INFERENCE_ENDPOINT = os.environ.get("HF_INFERENCE_ENDPOINT", "https://api-inference.huggingface.co")
+
 REPO_ID_SEPARATOR = "--"
 # ^ this substring is not allowed in repo_ids on hf.co
 # and is the canonical one we use for serialization of repo ids elsewhere.
@@ -83,11 +83,12 @@ default_cache_path = os.path.join(hf_cache_home, "hub")
 default_assets_cache_path = os.path.join(hf_cache_home, "assets")
 
 HUGGINGFACE_HUB_CACHE = os.getenv("HUGGINGFACE_HUB_CACHE", default_cache_path)
-HUGGINGFACE_ASSETS_CACHE = os.getenv(
-    "HUGGINGFACE_ASSETS_CACHE", default_assets_cache_path
-)
+HUGGINGFACE_ASSETS_CACHE = os.getenv("HUGGINGFACE_ASSETS_CACHE", default_assets_cache_path)
+
+HF_HUB_OFFLINE = _is_true(os.environ.get("HF_HUB_OFFLINE") or os.environ.get("TRANSFORMERS_OFFLINE"))
 
-HF_HUB_OFFLINE = _is_true(os.environ.get("HF_HUB_OFFLINE"))
+# Opt-out from telemetry requests
+HF_HUB_DISABLE_TELEMETRY = _is_true(os.environ.get("HF_HUB_DISABLE_TELEMETRY") or os.environ.get("DISABLE_TELEMETRY"))
 
 # In the past, token was stored in a hardcoded location
 # `_OLD_HF_TOKEN_PATH` is deprecated and will be removed "at some point".
@@ -103,23 +104,25 @@ HF_TOKEN_PATH = os.path.join(hf_cache_home, "token")
 # TL;DR: env variable has priority over code
 __HF_HUB_DISABLE_PROGRESS_BARS = os.environ.get("HF_HUB_DISABLE_PROGRESS_BARS")
 HF_HUB_DISABLE_PROGRESS_BARS: Optional[bool] = (
-    _is_true(__HF_HUB_DISABLE_PROGRESS_BARS)
-    if __HF_HUB_DISABLE_PROGRESS_BARS is not None
-    else None
+    _is_true(__HF_HUB_DISABLE_PROGRESS_BARS) if __HF_HUB_DISABLE_PROGRESS_BARS is not None else None
 )
 
 # Disable warning on machines that do not support symlinks (e.g. Windows non-developer)
-HF_HUB_DISABLE_SYMLINKS_WARNING: bool = _is_true(
-    os.environ.get("HF_HUB_DISABLE_SYMLINKS_WARNING")
-)
+HF_HUB_DISABLE_SYMLINKS_WARNING: bool = _is_true(os.environ.get("HF_HUB_DISABLE_SYMLINKS_WARNING"))
 
 # 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")
-)
+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"))
+
+
+# Used if download to `local_dir` and `local_dir_use_symlinks="auto"`
+# Files smaller than 5MB are copy-pasted while bigger files are symlinked. The idea is to save disk-usage by symlinking
+# huge files (i.e. LFS files most of the time) while allowing small files to be manually edited in local folder.
+HF_HUB_LOCAL_DIR_AUTO_SYMLINK_THRESHOLD: int = (
+    _as_int(os.environ.get("HF_HUB_LOCAL_DIR_AUTO_SYMLINK_THRESHOLD")) or 5 * 1024 * 1024
+)