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

huggingface_hub/templates/modelcard_template.md

@@ -10,9 +10,9 @@
 
 {{ model_summary | default("", true) }}
 
-# Model Details
+## Model Details
 
-## Model Description
+### Model Description
 
 <!-- Provide a longer summary of what this model is. -->
 
@@ -25,7 +25,7 @@
 - **License:** {{ license | default("[More Information Needed]", true)}}
 - **Finetuned from model [optional]:** {{ finetuned_from | default("[More Information Needed]", true)}}
 
-## Model Sources [optional]
+### Model Sources [optional]
 
 <!-- Provide the basic links for the model. -->
 
@@ -33,107 +33,112 @@
 - **Paper [optional]:** {{ paper | default("[More Information Needed]", true)}}
 - **Demo [optional]:** {{ demo | default("[More Information Needed]", true)}}
 
-# Uses
+## Uses
 
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
-## Direct Use
+### Direct Use
 
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
 {{ direct_use | default("[More Information Needed]", true)}}
 
-## Downstream Use [optional]
+### Downstream Use [optional]
 
 <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
 
 {{ downstream_use | default("[More Information Needed]", true)}}
 
-## Out-of-Scope Use
+### Out-of-Scope Use
 
 <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
 {{ out_of_scope_use | default("[More Information Needed]", true)}}
 
-# Bias, Risks, and Limitations
+## Bias, Risks, and Limitations
 
 <!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
 {{ bias_risks_limitations | default("[More Information Needed]", true)}}
 
-## Recommendations
+### Recommendations
 
 <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
 {{ bias_recommendations | default("Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", true)}}
 
-## How to Get Started with the Model
+### How to Get Started with the Model
 
 Use the code below to get started with the model.
 
 {{ get_started_code | default("[More Information Needed]", true)}}
 
-# Training Details
+## Training Details
 
-## Training Data
+### Training Data
 
 <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
 {{ training_data | default("[More Information Needed]", true)}}
 
-## Training Procedure [optional]
+### Training Procedure 
 
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
-### Preprocessing
+#### Preprocessing [optional]
 
 {{ preprocessing | default("[More Information Needed]", true)}}
 
-### Speeds, Sizes, Times
+
+#### Training Hyperparameters
+
+- **Training regime:** {{ training_regime | default("[More Information Needed]", true)}} <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
 
 <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
 
 {{ speeds_sizes_times | default("[More Information Needed]", true)}}
 
-# Evaluation
+## Evaluation
 
 <!-- This section describes the evaluation protocols and provides the results. -->
 
-## Testing Data, Factors & Metrics
+### Testing Data, Factors & Metrics
 
-### Testing Data
+#### Testing Data
 
 <!-- This should link to a Data Card if possible. -->
 
 {{ testing_data | default("[More Information Needed]", true)}}
 
-### Factors
+#### Factors
 
 <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
 
 {{ testing_factors | default("[More Information Needed]", true)}}
 
-### Metrics
+#### Metrics
 
 <!-- These are the evaluation metrics being used, ideally with a description of why. -->
 
 {{ testing_metrics | default("[More Information Needed]", true)}}
 
-## Results
+### Results
 
 {{ results | default("[More Information Needed]", true)}}
 
-### Summary
+#### Summary
 
 {{ results_summary | default("", true) }}
 
-# Model Examination [optional]
+## Model Examination [optional]
 
 <!-- Relevant interpretability work for the model goes here -->
 
 {{ model_examination | default("[More Information Needed]", true)}}
 
-# Environmental Impact
+## Environmental Impact
 
 <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
 
@@ -145,25 +150,25 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 - **Compute Region:** {{ cloud_region | default("[More Information Needed]", true)}}
 - **Carbon Emitted:** {{ co2_emitted | default("[More Information Needed]", true)}}
 
-# Technical Specifications [optional]
+## Technical Specifications [optional]
 
-## Model Architecture and Objective
+### Model Architecture and Objective
 
 {{ model_specs | default("[More Information Needed]", true)}}
 
-## Compute Infrastructure
+### Compute Infrastructure
 
 {{ compute_infrastructure | default("[More Information Needed]", true)}}
 
-### Hardware
+#### Hardware
 
 {{ hardware | default("[More Information Needed]", true)}}
 
-### Software
+#### Software
 
 {{ software | default("[More Information Needed]", true)}}
 
-# Citation [optional]
+## Citation [optional]
 
 <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
 
@@ -175,21 +180,21 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 {{ citation_apa | default("[More Information Needed]", true)}}
 
-# Glossary [optional]
+## Glossary [optional]
 
 <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
 
 {{ glossary | default("[More Information Needed]", true)}}
 
-# More Information [optional]
+## More Information [optional]
 
 {{ more_information | default("[More Information Needed]", true)}}
 
-# Model Card Authors [optional]
+## Model Card Authors [optional]
 
 {{ model_card_authors | default("[More Information Needed]", true)}}
 
-# Model Card Contact
+## Model Card Contact
 
 {{ model_card_contact | default("[More Information Needed]", true)}}
 

huggingface_hub/utils/__init__.py

@@ -91,3 +91,4 @@ from .tqdm import (
     tqdm,
     tqdm_stream_file,
 )
+from ._telemetry import send_telemetry

huggingface_hub/utils/_cache_assets.py

@@ -129,10 +129,7 @@ def cached_assets_path(
     try:
         path.mkdir(exist_ok=True, parents=True)
     except (FileExistsError, NotADirectoryError):
-        raise ValueError(
-            "Corrupted assets folder: cannot create directory because of an existing"
-            f" file ({path})."
-        )
+        raise ValueError(f"Corrupted assets folder: cannot create directory because of an existing file ({path}).")
 
     # Return
     return path

huggingface_hub/utils/_cache_manager.py

@@ -430,9 +430,7 @@ class HFCacheInfo:
         """
         hashes_to_delete: Set[str] = set(revisions)
 
-        repos_with_revisions: Dict[
-            CachedRepoInfo, Set[CachedRevisionInfo]
-        ] = defaultdict(set)
+        repos_with_revisions: Dict[CachedRepoInfo, Set[CachedRevisionInfo]] = defaultdict(set)
 
         for repo in self.repos:
             for revision in repo.revisions:
@@ -441,10 +439,7 @@ class HFCacheInfo:
                     hashes_to_delete.remove(revision.commit_hash)
 
         if len(hashes_to_delete) > 0:
-            logger.warning(
-                "Revision(s) not found - cannot delete them:"
-                f" {', '.join(hashes_to_delete)}"
-            )
+            logger.warning(f"Revision(s) not found - cannot delete them: {', '.join(hashes_to_delete)}")
 
         delete_strategy_blobs: Set[Path] = set()
         delete_strategy_refs: Set[Path] = set()
@@ -591,8 +586,10 @@ def scan_cache_dir(cache_dir: Optional[Union[str, Path]] = None) -> HFCacheInfo:
     cache_dir = Path(cache_dir).expanduser().resolve()
     if not cache_dir.exists():
         raise CacheNotFound(
-            f"Cache directory not found: {cache_dir}. Please use `cache_dir` argument"
-            " or set `HUGGINGFACE_HUB_CACHE` environment variable.",
+            (
+                f"Cache directory not found: {cache_dir}. Please use `cache_dir`"
+                " argument or set `HUGGINGFACE_HUB_CACHE` environment variable."
+            ),
             cache_dir=cache_dir,
         )
 
@@ -627,9 +624,7 @@ def _scan_cached_repo(repo_path: Path) -> CachedRepoInfo:
         raise CorruptedCacheException(f"Repo path is not a directory: {repo_path}")
 
     if "--" not in repo_path.name:
-        raise CorruptedCacheException(
-            f"Repo path is not a valid HuggingFace cache directory: {repo_path}"
-        )
+        raise CorruptedCacheException(f"Repo path is not a valid HuggingFace cache directory: {repo_path}")
 
     repo_type, repo_id = repo_path.name.split("--", maxsplit=1)
     repo_type = repo_type[:-1]  # "models" -> "model"
@@ -637,8 +632,7 @@ def _scan_cached_repo(repo_path: Path) -> CachedRepoInfo:
 
     if repo_type not in {"dataset", "model", "space"}:
         raise CorruptedCacheException(
-            f"Repo type must be `dataset`, `model` or `space`, found `{repo_type}`"
-            f" ({repo_path})."
+            f"Repo type must be `dataset`, `model` or `space`, found `{repo_type}` ({repo_path})."
         )
 
     blob_stats: Dict[Path, os.stat_result] = {}  # Key is blob_path, value is blob stats
@@ -647,9 +641,7 @@ def _scan_cached_repo(repo_path: Path) -> CachedRepoInfo:
     refs_path = repo_path / "refs"
 
     if not snapshots_path.exists() or not snapshots_path.is_dir():
-        raise CorruptedCacheException(
-            f"Snapshots dir doesn't exist in cached repo: {snapshots_path}"
-        )
+        raise CorruptedCacheException(f"Snapshots dir doesn't exist in cached repo: {snapshots_path}")
 
     # Scan over `refs` directory
 
@@ -663,9 +655,7 @@ def _scan_cached_repo(repo_path: Path) -> CachedRepoInfo:
         #         └── pr
         #             └── 1
         if refs_path.is_file():
-            raise CorruptedCacheException(
-                f"Refs directory cannot be a file: {refs_path}"
-            )
+            raise CorruptedCacheException(f"Refs directory cannot be a file: {refs_path}")
 
         for ref_path in refs_path.glob("**/*"):
             # glob("**/*") iterates over all files and directories -> skip directories
@@ -682,9 +672,7 @@ def _scan_cached_repo(repo_path: Path) -> CachedRepoInfo:
     cached_revisions: Set[CachedRevisionInfo] = set()
     for revision_path in snapshots_path.iterdir():
         if revision_path.is_file():
-            raise CorruptedCacheException(
-                f"Snapshots folder corrupted. Found a file: {revision_path}"
-            )
+            raise CorruptedCacheException(f"Snapshots folder corrupted. Found a file: {revision_path}")
 
         cached_files = set()
         for file_path in revision_path.glob("**/*"):
@@ -694,9 +682,7 @@ def _scan_cached_repo(repo_path: Path) -> CachedRepoInfo:
 
             blob_path = Path(file_path).resolve()
             if not blob_path.exists():
-                raise CorruptedCacheException(
-                    f"Blob missing (broken symlink): {blob_path}"
-                )
+                raise CorruptedCacheException(f"Blob missing (broken symlink): {blob_path}")
 
             if blob_path not in blob_stats:
                 blob_stats[blob_path] = blob_path.stat()
@@ -715,9 +701,7 @@ def _scan_cached_repo(repo_path: Path) -> CachedRepoInfo:
         # Last modified is either the last modified blob file or the revision folder
         # itself if it is empty
         if len(cached_files) > 0:
-            revision_last_modified = max(
-                blob_stats[file.blob_path].st_mtime for file in cached_files
-            )
+            revision_last_modified = max(blob_stats[file.blob_path].st_mtime for file in cached_files)
         else:
             revision_last_modified = revision_path.stat().st_mtime
 
@@ -727,8 +711,7 @@ def _scan_cached_repo(repo_path: Path) -> CachedRepoInfo:
                 files=frozenset(cached_files),
                 refs=frozenset(refs_by_hash.pop(revision_path.name, set())),
                 size_on_disk=sum(
-                    blob_stats[blob_path].st_size
-                    for blob_path in set(file.blob_path for file in cached_files)
+                    blob_stats[blob_path].st_size for blob_path in set(file.blob_path for file in cached_files)
                 ),
                 snapshot_path=revision_path,
                 last_modified=revision_last_modified,
@@ -738,8 +721,7 @@ def _scan_cached_repo(repo_path: Path) -> CachedRepoInfo:
     # Check that all refs referred to an existing revision
     if len(refs_by_hash) > 0:
         raise CorruptedCacheException(
-            "Reference(s) refer to missing commit hashes:"
-            f" {dict(refs_by_hash)} ({repo_path})."
+            f"Reference(s) refer to missing commit hashes: {dict(refs_by_hash)} ({repo_path})."
         )
 
     # Last modified is either the last modified blob file or the repo folder itself if
@@ -823,10 +805,6 @@ def _try_delete_path(path: Path, path_type: str) -> None:
         else:
             shutil.rmtree(path)
     except FileNotFoundError:
-        logger.warning(
-            f"Couldn't delete {path_type}: file not found ({path})", exc_info=True
-        )
+        logger.warning(f"Couldn't delete {path_type}: file not found ({path})", exc_info=True)
     except PermissionError:
-        logger.warning(
-            f"Couldn't delete {path_type}: permission denied ({path})", exc_info=True
-        )
+        logger.warning(f"Couldn't delete {path_type}: permission denied ({path})", exc_info=True)

huggingface_hub/utils/_deprecation.py

@@ -36,9 +36,11 @@ def _deprecate_positional_args(*, version: str):
             ]
             args_msg = ", ".join(args_msg)
             warnings.warn(
-                f"Deprecated positional argument(s) used in '{f.__name__}': pass"
-                f" {args_msg} as keyword args. From version {version} passing these as"
-                " positional arguments will result in an error,",
+                (
+                    f"Deprecated positional argument(s) used in '{f.__name__}': pass"
+                    f" {args_msg} as keyword args. From version {version} passing these"
+                    " as positional arguments will result in an error,"
+                ),
                 FutureWarning,
             )
             kwargs.update(zip(sig.parameters, args))
@@ -120,8 +122,7 @@ def _deprecate_method(*, version: str, message: Optional[str] = None):
         @wraps(f)
         def inner_f(*args, **kwargs):
             warning_message = (
-                f"'{f.__name__}' (from '{f.__module__}') is deprecated and will be"
-                f" removed from version '{version}'."
+                f"'{f.__name__}' (from '{f.__module__}') is deprecated and will be removed from version '{version}'."
             )
             if message is not None:
                 warning_message += " " + message
@@ -189,14 +190,9 @@ class DeprecateListMetaclass(type):
     def __new__(cls, clsname, bases, attrs):
         # Check consistency
         if "_deprecate" not in attrs:
-            raise TypeError(
-                "A `_deprecate` method must be implemented to use"
-                " `DeprecateListMetaclass`."
-            )
+            raise TypeError("A `_deprecate` method must be implemented to use `DeprecateListMetaclass`.")
         if list not in bases:
-            raise TypeError(
-                "Class must inherit from `list` to use `DeprecateListMetaclass`."
-            )
+            raise TypeError("Class must inherit from `list` to use `DeprecateListMetaclass`.")
 
         # Create decorator to deprecate list-only methods, including magic ones
         def _with_deprecation(f, name):

huggingface_hub/utils/_errors.py

@@ -2,7 +2,6 @@ from typing import Optional
 
 from requests import HTTPError, Response
 
-from ._deprecation import _deprecate_method
 from ._fixes import JSONDecodeError
 
 
@@ -39,7 +38,7 @@ class HfHubHTTPError(HTTPError):
     request_id: Optional[str] = None
     server_message: Optional[str] = None
 
-    def __init__(self, message: str, response: Optional[Response]):
+    def __init__(self, message: str, response: Optional[Response] = None):
         # Parse server information if any.
         if response is not None:
             self.request_id = response.headers.get("X-Request-Id")
@@ -52,9 +51,7 @@ class HfHubHTTPError(HTTPError):
             server_message_from_headers = response.headers.get("X-Error-Message")
             server_message_from_body = server_data.get("error")
             server_multiple_messages_from_body = "\n".join(
-                error["message"]
-                for error in server_data.get("errors", [])
-                if "message" in error
+                error["message"] for error in server_data.get("errors", []) if "message" in error
             )
 
             # Concatenate error messages
@@ -203,9 +200,7 @@ class BadRequestError(HfHubHTTPError, ValueError):
     """
 
 
-def hf_raise_for_status(
-    response: Response, endpoint_name: Optional[str] = None
-) -> None:
+def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None) -> None:
     """
     Internal version of `response.raise_for_status()` that will refine a
     potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`.
@@ -266,26 +261,16 @@ def hf_raise_for_status(
         error_code = response.headers.get("X-Error-Code")
 
         if error_code == "RevisionNotFound":
-            message = (
-                f"{response.status_code} Client Error."
-                + "\n\n"
-                + f"Revision Not Found for url: {response.url}."
-            )
+            message = f"{response.status_code} Client Error." + "\n\n" + f"Revision Not Found for url: {response.url}."
             raise RevisionNotFoundError(message, response) from e
 
         elif error_code == "EntryNotFound":
-            message = (
-                f"{response.status_code} Client Error."
-                + "\n\n"
-                + f"Entry Not Found for url: {response.url}."
-            )
+            message = f"{response.status_code} Client Error." + "\n\n" + f"Entry Not Found for url: {response.url}."
             raise EntryNotFoundError(message, response) from e
 
         elif error_code == "GatedRepo":
             message = (
-                f"{response.status_code} Client Error."
-                + "\n\n"
-                + f"Cannot access gated repo for url {response.url}."
+                f"{response.status_code} Client Error." + "\n\n" + f"Cannot access gated repo for url {response.url}."
             )
             raise GatedRepoError(message, response) from e
 
@@ -307,9 +292,7 @@ def hf_raise_for_status(
 
         elif response.status_code == 400:
             message = (
-                f"\n\nBad request for {endpoint_name} endpoint:"
-                if endpoint_name is not None
-                else "\n\nBad request:"
+                f"\n\nBad request for {endpoint_name} endpoint:" if endpoint_name is not None else "\n\nBad request:"
             )
             raise BadRequestError(message, response=response) from e
 
@@ -318,31 +301,7 @@ def hf_raise_for_status(
         raise HfHubHTTPError(str(e), response=response) from e
 
 
-@_deprecate_method(version="0.13", message="Use `hf_raise_for_status` instead.")
-def _raise_for_status(response):
-    """Keep alias for now."""
-    hf_raise_for_status(response)
-
-
-@_deprecate_method(version="0.13", message="Use `hf_raise_for_status` instead.")
-def _raise_with_request_id(response):
-    """Keep alias for now."""
-    hf_raise_for_status(response)
-
-
-@_deprecate_method(version="0.13", message="Use `hf_raise_for_status` instead.")
-def _raise_convert_bad_request(response: Response, endpoint_name: str):
-    """
-    Calls hf_raise_for_status on resp and converts HTTP 400 errors into ValueError.
-
-    Keep alias for now.
-    """
-    hf_raise_for_status(response, endpoint_name=endpoint_name)
-
-
-def _format_error_message(
-    message: str, request_id: Optional[str], server_message: Optional[str]
-) -> str:
+def _format_error_message(message: str, request_id: Optional[str], server_message: Optional[str]) -> str:
     """
     Format the `HfHubHTTPError` error message based on initial message and information
     returned by the server.
@@ -350,11 +309,7 @@ def _format_error_message(
     Used when initializing `HfHubHTTPError`.
     """
     # Add message from response body
-    if (
-        server_message is not None
-        and len(server_message) > 0
-        and server_message.lower() not in message.lower()
-    ):
+    if server_message is not None and len(server_message) > 0 and server_message.lower() not in message.lower():
         if "\n\n" in message:
             message += "\n" + server_message
         else:
@@ -365,9 +320,7 @@ def _format_error_message(
         request_id_message = f" (Request ID: {request_id})"
         if "\n" in message:
             newline_index = message.index("\n")
-            message = (
-                message[:newline_index] + request_id_message + message[newline_index:]
-            )
+            message = message[:newline_index] + request_id_message + message[newline_index:]
         else:
             message += request_id_message
 

huggingface_hub/utils/_fixes.py

@@ -31,9 +31,7 @@ import yaml
 # >>> yaml_dump({"emoji": "👀", "some unicode": "日本か"})
 # 'emoji: "👀"\nsome unicode: "日本か"\n'
 # ```
-yaml_dump: Callable[..., str] = partial(  # type: ignore
-    yaml.dump, stream=None, allow_unicode=True
-)
+yaml_dump: Callable[..., str] = partial(yaml.dump, stream=None, allow_unicode=True)  # type: ignore
 
 
 @contextlib.contextmanager
@@ -53,9 +51,7 @@ def SoftTemporaryDirectory(
 
     See https://www.scivision.dev/python-tempfile-permission-error-windows/.
     """
-    tmpdir = tempfile.TemporaryDirectory(
-        prefix=prefix, suffix=suffix, dir=dir, **kwargs
-    )
+    tmpdir = tempfile.TemporaryDirectory(prefix=prefix, suffix=suffix, dir=dir, **kwargs)
     yield tmpdir.name
 
     try:

huggingface_hub/utils/_git_credential.py

@@ -40,18 +40,14 @@ def list_credential_helpers(folder: Optional[str] = None) -> List[str]:
         #       See: https://github.com/huggingface/huggingface_hub/pull/1138#discussion_r1013324508
         return sorted(  # Sort for nice printing
             {  # Might have some duplicates
-                line.split("=")[-1].split()[0]
-                for line in output.split("\n")
-                if "credential.helper" in line
+                line.split("=")[-1].split()[0] for line in output.split("\n") if "credential.helper" in line
             }
         )
     except subprocess.CalledProcessError as exc:
         raise EnvironmentError(exc.stderr)
 
 
-def set_git_credential(
-    token: str, username: str = "hf_user", folder: Optional[str] = None
-) -> None:
+def set_git_credential(token: str, username: str = "hf_user", folder: Optional[str] = None) -> None:
     """Save a username/token pair in git credential for HF Hub registry.
 
     Credentials are saved in all configured helpers (store, cache, macOS keychain,...).
@@ -70,15 +66,11 @@ def set_git_credential(
         stdin,
         _,
     ):
-        stdin.write(
-            f"url={ENDPOINT}\nusername={username.lower()}\npassword={token}\n\n"
-        )
+        stdin.write(f"url={ENDPOINT}\nusername={username.lower()}\npassword={token}\n\n")
         stdin.flush()
 
 
-def unset_git_credential(
-    username: str = "hf_user", folder: Optional[str] = None
-) -> None:
+def unset_git_credential(username: str = "hf_user", folder: Optional[str] = None) -> None:
     """Erase credentials from git credential for HF Hub registry.
 
     Credentials are erased from the configured helpers (store, cache, macOS
@@ -122,10 +114,7 @@ def write_to_credential_store(username: str, password: str) -> None:
 
 @_deprecate_method(
     version="0.14",
-    message=(
-        "Please open an issue on https://github.com/huggingface/huggingface_hub if this"
-        " a useful feature for you."
-    ),
+    message="Please open an issue on https://github.com/huggingface/huggingface_hub if this a useful feature for you.",
 )
 def read_from_credential_store(
     username: Optional[str] = None,