huggingface-hub 0.35.0rc0__py3-none-any.whl → 1.0.0rc0__py3-none-any.whl

huggingface_hub/lfs.py

@@ -14,7 +14,6 @@
 # limitations under the License.
 """Git LFS related type definitions and utilities"""
 
-import inspect
 import io
 import re
 import warnings
@@ -22,7 +21,7 @@ from dataclasses import dataclass
 from math import ceil
 from os.path import getsize
 from pathlib import Path
-from typing import TYPE_CHECKING, BinaryIO, Dict, Iterable, List, Optional, Tuple, TypedDict
+from typing import TYPE_CHECKING, BinaryIO, Iterable, Optional, TypedDict
 from urllib.parse import unquote
 
 from huggingface_hub import constants
@@ -107,8 +106,8 @@ def post_lfs_batch_info(
     repo_id: str,
     revision: Optional[str] = None,
     endpoint: Optional[str] = None,
-    headers: Optional[Dict[str, str]] = None,
-) -> Tuple[List[dict], List[dict]]:
+    headers: Optional[dict[str, str]] = None,
+) -> tuple[list[dict], list[dict]]:
     """
     Requests the LFS batch endpoint to retrieve upload instructions
 
@@ -136,7 +135,7 @@ def post_lfs_batch_info(
     Raises:
         [`ValueError`](https://docs.python.org/3/library/exceptions.html#ValueError)
             If an argument is invalid or the server response is malformed.
-        [`HTTPError`](https://requests.readthedocs.io/en/latest/api/#requests.HTTPError)
+        [`HfHubHTTPError`]
             If the server returned an error.
     """
     endpoint = endpoint if endpoint is not None else constants.ENDPOINT
@@ -144,7 +143,7 @@ def post_lfs_batch_info(
     if repo_type in constants.REPO_TYPES_URL_PREFIXES:
         url_prefix = constants.REPO_TYPES_URL_PREFIXES[repo_type]
     batch_url = f"{endpoint}/{url_prefix}{repo_id}.git/info/lfs/objects/batch"
-    payload: Dict = {
+    payload: dict = {
         "operation": "upload",
         "transfers": ["basic", "multipart"],
         "objects": [
@@ -187,14 +186,14 @@ class CompletionPayloadT(TypedDict):
     """Payload that will be sent to the Hub when uploading multi-part."""
 
     oid: str
-    parts: List[PayloadPartT]
+    parts: list[PayloadPartT]
 
 
 def lfs_upload(
     operation: "CommitOperationAdd",
-    lfs_batch_action: Dict,
+    lfs_batch_action: dict,
     token: Optional[str] = None,
-    headers: Optional[Dict[str, str]] = None,
+    headers: Optional[dict[str, str]] = None,
     endpoint: Optional[str] = None,
 ) -> None:
     """
@@ -214,7 +213,7 @@ def lfs_upload(
     Raises:
         [`ValueError`](https://docs.python.org/3/library/exceptions.html#ValueError)
             If `lfs_batch_action` is improperly formatted
-        [`HTTPError`](https://requests.readthedocs.io/en/latest/api/#requests.HTTPError)
+        [`HfHubHTTPError`]
             If the upload resulted in an error
     """
     # 0. If LFS file is already present, skip upload
@@ -308,11 +307,9 @@ def _upload_single_part(operation: "CommitOperationAdd", upload_url: str) -> Non
         fileobj:
             The file-like object holding the data to upload.
 
-    Returns: `requests.Response`
-
     Raises:
-     [`HTTPError`](https://requests.readthedocs.io/en/latest/api/#requests.HTTPError)
-        If the upload resulted in an error.
+        [`HfHubHTTPError`]
+            If the upload resulted in an error.
     """
     with operation.as_file(with_tqdm=True) as fileobj:
         # S3 might raise a transient 500 error -> let's retry if that happens
@@ -320,7 +317,7 @@ def _upload_single_part(operation: "CommitOperationAdd", upload_url: str) -> Non
         hf_raise_for_status(response)
 
 
-def _upload_multi_part(operation: "CommitOperationAdd", header: Dict, chunk_size: int, upload_url: str) -> None:
+def _upload_multi_part(operation: "CommitOperationAdd", header: dict, chunk_size: int, upload_url: str) -> None:
     """
     Uploads file using HF multipart LFS transfer protocol.
     """
@@ -355,7 +352,7 @@ def _upload_multi_part(operation: "CommitOperationAdd", header: Dict, chunk_size
     hf_raise_for_status(completion_res)
 
 
-def _get_sorted_parts_urls(header: Dict, upload_info: UploadInfo, chunk_size: int) -> List[str]:
+def _get_sorted_parts_urls(header: dict, upload_info: UploadInfo, chunk_size: int) -> list[str]:
     sorted_part_upload_urls = [
         upload_url
         for _, upload_url in sorted(
@@ -373,8 +370,8 @@ def _get_sorted_parts_urls(header: Dict, upload_info: UploadInfo, chunk_size: in
     return sorted_part_upload_urls
 
 
-def _get_completion_payload(response_headers: List[Dict], oid: str) -> CompletionPayloadT:
-    parts: List[PayloadPartT] = []
+def _get_completion_payload(response_headers: list[dict], oid: str) -> CompletionPayloadT:
+    parts: list[PayloadPartT] = []
     for part_number, header in enumerate(response_headers):
         etag = header.get("etag")
         if etag is None or etag == "":
@@ -389,8 +386,8 @@ def _get_completion_payload(response_headers: List[Dict], oid: str) -> Completio
 
 
 def _upload_parts_iteratively(
-    operation: "CommitOperationAdd", sorted_parts_urls: List[str], chunk_size: int
-) -> List[Dict]:
+    operation: "CommitOperationAdd", sorted_parts_urls: list[str], chunk_size: int
+) -> list[dict]:
     headers = []
     with operation.as_file(with_tqdm=True) as fileobj:
         for part_idx, part_upload_url in enumerate(sorted_parts_urls):
@@ -409,8 +406,8 @@ def _upload_parts_iteratively(
 
 
 def _upload_parts_hf_transfer(
-    operation: "CommitOperationAdd", sorted_parts_urls: List[str], chunk_size: int
-) -> List[Dict]:
+    operation: "CommitOperationAdd", sorted_parts_urls: list[str], chunk_size: int
+) -> list[dict]:
     # Upload file using an external Rust-based package. Upload is faster but support less features (no progress bars).
     try:
         from hf_transfer import multipart_upload
@@ -420,12 +417,6 @@ def _upload_parts_hf_transfer(
             " not available in your environment. Try `pip install hf_transfer`."
         )
 
-    supports_callback = "callback" in inspect.signature(multipart_upload).parameters
-    if not supports_callback:
-        warnings.warn(
-            "You are using an outdated version of `hf_transfer`. Consider upgrading to latest version to enable progress bars using `pip install -U hf_transfer`."
-        )
-
     total = operation.upload_info.size
     desc = operation.path_in_repo
     if len(desc) > 40:
@@ -448,13 +439,11 @@ def _upload_parts_hf_transfer(
                 max_files=128,
                 parallel_failures=127,  # could be removed
                 max_retries=5,
-                **({"callback": progress.update} if supports_callback else {}),
+                callback=progress.update,
             )
         except Exception as e:
             raise RuntimeError(
                 "An error occurred while uploading using `hf_transfer`. Consider disabling HF_HUB_ENABLE_HF_TRANSFER for"
                 " better error handling."
             ) from e
-        if not supports_callback:
-            progress.update(total)
         return output

huggingface_hub/repocard.py

@@ -1,9 +1,8 @@
 import os
 import re
 from pathlib import Path
-from typing import Any, Dict, Literal, Optional, Type, Union
+from typing import Any, Literal, Optional, Union
 
-import requests
 import yaml
 
 from huggingface_hub.file_download import hf_hub_download
@@ -17,7 +16,7 @@ from huggingface_hub.repocard_data import (
     eval_results_to_model_index,
     model_index_to_eval_results,
 )
-from huggingface_hub.utils import get_session, is_jinja_available, yaml_dump
+from huggingface_hub.utils import HfHubHTTPError, get_session, hf_raise_for_status, is_jinja_available, yaml_dump
 
 from . import constants
 from .errors import EntryNotFoundError
@@ -204,7 +203,7 @@ class RepoCard:
 
             - [`ValueError`](https://docs.python.org/3/library/exceptions.html#ValueError)
               if the card fails validation checks.
-            - [`HTTPError`](https://requests.readthedocs.io/en/latest/api/#requests.HTTPError)
+            - [`HfHubHTTPError`]
               if the request to the Hub API fails for any other reason.
 
         </Tip>
@@ -220,11 +219,11 @@ class RepoCard:
         headers = {"Accept": "text/plain"}
 
         try:
-            r = get_session().post("https://huggingface.co/api/validate-yaml", body, headers=headers)
-            r.raise_for_status()
-        except requests.exceptions.HTTPError as exc:
-            if r.status_code == 400:
-                raise ValueError(r.text)
+            response = get_session().post("https://huggingface.co/api/validate-yaml", json=body, headers=headers)
+            hf_raise_for_status(response)
+        except HfHubHTTPError as exc:
+            if response.status_code == 400:
+                raise ValueError(response.text)
             else:
                 raise exc
 
@@ -336,7 +335,7 @@ class RepoCard:
 
 
 class ModelCard(RepoCard):
-    card_data_class = ModelCardData
+    card_data_class = ModelCardData  # type: ignore[assignment]
     default_template_path = TEMPLATE_MODELCARD_PATH
     repo_type = "model"
 
@@ -417,7 +416,7 @@ class ModelCard(RepoCard):
 
 
 class DatasetCard(RepoCard):
-    card_data_class = DatasetCardData
+    card_data_class = DatasetCardData  # type: ignore[assignment]
     default_template_path = TEMPLATE_DATASETCARD_PATH
     repo_type = "dataset"
 
@@ -482,7 +481,7 @@ class DatasetCard(RepoCard):
 
 
 class SpaceCard(RepoCard):
-    card_data_class = SpaceCardData
+    card_data_class = SpaceCardData  # type: ignore[assignment]
     default_template_path = TEMPLATE_MODELCARD_PATH
     repo_type = "space"
 
@@ -508,7 +507,7 @@ def _detect_line_ending(content: str) -> Literal["\r", "\n", "\r\n", None]:  # n
         return "\n"
 
 
-def metadata_load(local_path: Union[str, Path]) -> Optional[Dict]:
+def metadata_load(local_path: Union[str, Path]) -> Optional[dict]:
     content = Path(local_path).read_text()
     match = REGEX_YAML_BLOCK.search(content)
     if match:
@@ -521,7 +520,7 @@ def metadata_load(local_path: Union[str, Path]) -> Optional[Dict]:
         return None
 
 
-def metadata_save(local_path: Union[str, Path], data: Dict) -> None:
+def metadata_save(local_path: Union[str, Path], data: dict) -> None:
     """
     Save the metadata dict in the upper YAML part Trying to preserve newlines as
     in the existing file. Docs about open() with newline="" parameter:
@@ -569,7 +568,7 @@ def metadata_eval_result(
     dataset_split: Optional[str] = None,
     dataset_revision: Optional[str] = None,
     metrics_verification_token: Optional[str] = None,
-) -> Dict:
+) -> dict:
     """
     Creates a metadata dict with the result from a model evaluated on a dataset.
 
@@ -684,7 +683,7 @@ def metadata_eval_result(
 @validate_hf_hub_args
 def metadata_update(
     repo_id: str,
-    metadata: Dict,
+    metadata: dict,
     *,
     repo_type: Optional[str] = None,
     overwrite: bool = False,
@@ -752,7 +751,7 @@ def metadata_update(
     commit_message = commit_message if commit_message is not None else "Update metadata with huggingface_hub"
 
     # Card class given repo_type
-    card_class: Type[RepoCard]
+    card_class: type[RepoCard]
     if repo_type is None or repo_type == "model":
         card_class = ModelCard
     elif repo_type == "dataset":
@@ -771,7 +770,8 @@ def metadata_update(
             raise ValueError("Cannot update metadata on a Space that doesn't contain a `README.md` file.")
 
         # Initialize a ModelCard or DatasetCard from default template and no data.
-        card = card_class.from_template(CardData())
+        # Cast to the concrete expected card type to satisfy type checkers.
+        card = card_class.from_template(CardData())  # type: ignore[return-value]
 
     for key, value in metadata.items():
         if key == "model-index":

huggingface_hub/repocard_data.py

@@ -1,7 +1,7 @@
 import copy
 from collections import defaultdict
 from dataclasses import dataclass
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Any, Optional, Union
 
 from huggingface_hub.utils import logging, yaml_dump
 
@@ -38,7 +38,7 @@ class EvalResult:
         dataset_revision (`str`, *optional*):
             The revision (AKA Git Sha) of the dataset used in `load_dataset()`.
             Example: 5503434ddd753f426f4b38109466949a1217c2bb
-        dataset_args (`Dict[str, Any]`, *optional*):
+        dataset_args (`dict[str, Any]`, *optional*):
             The arguments passed during `Metric.compute()`. Example for `bleu`: `{"max_order": 4}`
         metric_name (`str`, *optional*):
             A pretty name for the metric. Example: "Test WER".
@@ -46,7 +46,7 @@ class EvalResult:
             The name of the metric configuration used in `load_metric()`.
             Example: bleurt-large-512 in `load_metric("bleurt", "bleurt-large-512")`.
             See the `datasets` docs for more info: https://huggingface.co/docs/datasets/v2.1.0/en/loading#load-configurations
-        metric_args (`Dict[str, Any]`, *optional*):
+        metric_args (`dict[str, Any]`, *optional*):
             The arguments passed during `Metric.compute()`. Example for `bleu`: max_order: 4
         verified (`bool`, *optional*):
             Indicates whether the metrics originate from Hugging Face's [evaluation service](https://huggingface.co/spaces/autoevaluate/model-evaluator) or not. Automatically computed by Hugging Face, do not set.
@@ -102,7 +102,7 @@ class EvalResult:
 
     # The arguments passed during `Metric.compute()`.
     # Example for `bleu`: max_order: 4
-    dataset_args: Optional[Dict[str, Any]] = None
+    dataset_args: Optional[dict[str, Any]] = None
 
     # A pretty name for the metric.
     # Example: Test WER
@@ -115,7 +115,7 @@ class EvalResult:
 
     # The arguments passed during `Metric.compute()`.
     # Example for `bleu`: max_order: 4
-    metric_args: Optional[Dict[str, Any]] = None
+    metric_args: Optional[dict[str, Any]] = None
 
     # Indicates whether the metrics originate from Hugging Face's [evaluation service](https://huggingface.co/spaces/autoevaluate/model-evaluator) or not. Automatically computed by Hugging Face, do not set.
     verified: Optional[bool] = None
@@ -195,7 +195,7 @@ class CardData:
         """
         pass
 
-    def to_yaml(self, line_break=None, original_order: Optional[List[str]] = None) -> str:
+    def to_yaml(self, line_break=None, original_order: Optional[list[str]] = None) -> str:
         """Dumps CardData to a YAML block for inclusion in a README.md file.
 
         Args:
@@ -246,9 +246,9 @@ class CardData:
 
 
 def _validate_eval_results(
-    eval_results: Optional[Union[EvalResult, List[EvalResult]]],
+    eval_results: Optional[Union[EvalResult, list[EvalResult]]],
     model_name: Optional[str],
-) -> List[EvalResult]:
+) -> list[EvalResult]:
     if eval_results is None:
         return []
     if isinstance(eval_results, EvalResult):
@@ -266,17 +266,17 @@ class ModelCardData(CardData):
     """Model Card Metadata that is used by Hugging Face Hub when included at the top of your README.md
 
     Args:
-        base_model (`str` or `List[str]`, *optional*):
+        base_model (`str` or `list[str]`, *optional*):
             The identifier of the base model from which the model derives. This is applicable for example if your model is a
             fine-tune or adapter of an existing model. The value must be the ID of a model on the Hub (or a list of IDs
             if your model derives from multiple models). Defaults to None.
-        datasets (`Union[str, List[str]]`, *optional*):
+        datasets (`Union[str, list[str]]`, *optional*):
             Dataset or list of datasets that were used to train this model. Should be a dataset ID
             found on https://hf.co/datasets. Defaults to None.
-        eval_results (`Union[List[EvalResult], EvalResult]`, *optional*):
+        eval_results (`Union[list[EvalResult], EvalResult]`, *optional*):
             List of `huggingface_hub.EvalResult` that define evaluation results of the model. If provided,
             `model_name` is used to as a name on PapersWithCode's leaderboards. Defaults to `None`.
-        language (`Union[str, List[str]]`, *optional*):
+        language (`Union[str, list[str]]`, *optional*):
             Language of model's training data or metadata. It must be an ISO 639-1, 639-2 or
             639-3 code (two/three letters), or a special value like "code", "multilingual". Defaults to `None`.
         library_name (`str`, *optional*):
@@ -292,7 +292,7 @@ class ModelCardData(CardData):
         license_link (`str`, *optional*):
             Link to the license of this model. Defaults to None. To be used in conjunction with `license_name`.
             Common licenses (Apache-2.0, MIT, CC-BY-SA-4.0) do not need a link. In that case, use `license` instead.
-        metrics (`List[str]`, *optional*):
+        metrics (`list[str]`, *optional*):
             List of metrics used to evaluate this model. Should be a metric name that can be found
             at https://hf.co/metrics. Example: 'accuracy'. Defaults to None.
         model_name (`str`, *optional*):
@@ -302,7 +302,7 @@ class ModelCardData(CardData):
             then the repo name is used as a default. Defaults to None.
         pipeline_tag (`str`, *optional*):
             The pipeline tag associated with the model. Example: "text-classification".
-        tags (`List[str]`, *optional*):
+        tags (`list[str]`, *optional*):
             List of tags to add to your model that can be used when filtering on the Hugging
             Face Hub. Defaults to None.
         ignore_metadata_errors (`str`):
@@ -329,18 +329,18 @@ class ModelCardData(CardData):
     def __init__(
         self,
         *,
-        base_model: Optional[Union[str, List[str]]] = None,
-        datasets: Optional[Union[str, List[str]]] = None,
-        eval_results: Optional[List[EvalResult]] = None,
-        language: Optional[Union[str, List[str]]] = None,
+        base_model: Optional[Union[str, list[str]]] = None,
+        datasets: Optional[Union[str, list[str]]] = None,
+        eval_results: Optional[list[EvalResult]] = None,
+        language: Optional[Union[str, list[str]]] = None,
         library_name: Optional[str] = None,
         license: Optional[str] = None,
         license_name: Optional[str] = None,
         license_link: Optional[str] = None,
-        metrics: Optional[List[str]] = None,
+        metrics: Optional[list[str]] = None,
         model_name: Optional[str] = None,
         pipeline_tag: Optional[str] = None,
-        tags: Optional[List[str]] = None,
+        tags: Optional[list[str]] = None,
         ignore_metadata_errors: bool = False,
         **kwargs,
     ):
@@ -395,58 +395,58 @@ class DatasetCardData(CardData):
     """Dataset Card Metadata that is used by Hugging Face Hub when included at the top of your README.md
 
     Args:
-        language (`List[str]`, *optional*):
+        language (`list[str]`, *optional*):
             Language of dataset's data or metadata. It must be an ISO 639-1, 639-2 or
             639-3 code (two/three letters), or a special value like "code", "multilingual".
-        license (`Union[str, List[str]]`, *optional*):
+        license (`Union[str, list[str]]`, *optional*):
             License(s) of this dataset. Example: apache-2.0 or any license from
             https://huggingface.co/docs/hub/repositories-licenses.
-        annotations_creators (`Union[str, List[str]]`, *optional*):
+        annotations_creators (`Union[str, list[str]]`, *optional*):
             How the annotations for the dataset were created.
             Options are: 'found', 'crowdsourced', 'expert-generated', 'machine-generated', 'no-annotation', 'other'.
-        language_creators (`Union[str, List[str]]`, *optional*):
+        language_creators (`Union[str, list[str]]`, *optional*):
             How the text-based data in the dataset was created.
             Options are: 'found', 'crowdsourced', 'expert-generated', 'machine-generated', 'other'
-        multilinguality (`Union[str, List[str]]`, *optional*):
+        multilinguality (`Union[str, list[str]]`, *optional*):
             Whether the dataset is multilingual.
             Options are: 'monolingual', 'multilingual', 'translation', 'other'.
-        size_categories (`Union[str, List[str]]`, *optional*):
+        size_categories (`Union[str, list[str]]`, *optional*):
             The number of examples in the dataset. Options are: 'n<1K', '1K<n<10K', '10K<n<100K',
             '100K<n<1M', '1M<n<10M', '10M<n<100M', '100M<n<1B', '1B<n<10B', '10B<n<100B', '100B<n<1T', 'n>1T', and 'other'.
-        source_datasets (`List[str]]`, *optional*):
+        source_datasets (`list[str]]`, *optional*):
             Indicates whether the dataset is an original dataset or extended from another existing dataset.
             Options are: 'original' and 'extended'.
-        task_categories (`Union[str, List[str]]`, *optional*):
+        task_categories (`Union[str, list[str]]`, *optional*):
             What categories of task does the dataset support?
-        task_ids (`Union[str, List[str]]`, *optional*):
+        task_ids (`Union[str, list[str]]`, *optional*):
             What specific tasks does the dataset support?
         paperswithcode_id (`str`, *optional*):
             ID of the dataset on PapersWithCode.
         pretty_name (`str`, *optional*):
             A more human-readable name for the dataset. (ex. "Cats vs. Dogs")
-        train_eval_index (`Dict`, *optional*):
+        train_eval_index (`dict`, *optional*):
             A dictionary that describes the necessary spec for doing evaluation on the Hub.
             If not provided, it will be gathered from the 'train-eval-index' key of the kwargs.
-        config_names (`Union[str, List[str]]`, *optional*):
+        config_names (`Union[str, list[str]]`, *optional*):
             A list of the available dataset configs for the dataset.
     """
 
     def __init__(
         self,
         *,
-        language: Optional[Union[str, List[str]]] = None,
-        license: Optional[Union[str, List[str]]] = None,
-        annotations_creators: Optional[Union[str, List[str]]] = None,
-        language_creators: Optional[Union[str, List[str]]] = None,
-        multilinguality: Optional[Union[str, List[str]]] = None,
-        size_categories: Optional[Union[str, List[str]]] = None,
-        source_datasets: Optional[List[str]] = None,
-        task_categories: Optional[Union[str, List[str]]] = None,
-        task_ids: Optional[Union[str, List[str]]] = None,
+        language: Optional[Union[str, list[str]]] = None,
+        license: Optional[Union[str, list[str]]] = None,
+        annotations_creators: Optional[Union[str, list[str]]] = None,
+        language_creators: Optional[Union[str, list[str]]] = None,
+        multilinguality: Optional[Union[str, list[str]]] = None,
+        size_categories: Optional[Union[str, list[str]]] = None,
+        source_datasets: Optional[list[str]] = None,
+        task_categories: Optional[Union[str, list[str]]] = None,
+        task_ids: Optional[Union[str, list[str]]] = None,
         paperswithcode_id: Optional[str] = None,
         pretty_name: Optional[str] = None,
-        train_eval_index: Optional[Dict] = None,
-        config_names: Optional[Union[str, List[str]]] = None,
+        train_eval_index: Optional[dict] = None,
+        config_names: Optional[Union[str, list[str]]] = None,
         ignore_metadata_errors: bool = False,
         **kwargs,
     ):
@@ -495,11 +495,11 @@ class SpaceCardData(CardData):
             https://huggingface.co/docs/hub/repositories-licenses.
         duplicated_from (`str`, *optional*)
             ID of the original Space if this is a duplicated Space.
-        models (List[`str`], *optional*)
+        models (list[`str`], *optional*)
             List of models related to this Space. Should be a dataset ID found on https://hf.co/models.
-        datasets (`List[str]`, *optional*)
+        datasets (`list[str]`, *optional*)
             List of datasets related to this Space. Should be a dataset ID found on https://hf.co/datasets.
-        tags (`List[str]`, *optional*)
+        tags (`list[str]`, *optional*)
             List of tags to add to your Space that can be used when filtering on the Hub.
         ignore_metadata_errors (`str`):
             If True, errors while parsing the metadata section will be ignored. Some information might be lost during
@@ -532,9 +532,9 @@ class SpaceCardData(CardData):
         app_port: Optional[int] = None,
         license: Optional[str] = None,
         duplicated_from: Optional[str] = None,
-        models: Optional[List[str]] = None,
-        datasets: Optional[List[str]] = None,
-        tags: Optional[List[str]] = None,
+        models: Optional[list[str]] = None,
+        datasets: Optional[list[str]] = None,
+        tags: Optional[list[str]] = None,
         ignore_metadata_errors: bool = False,
         **kwargs,
     ):
@@ -552,14 +552,14 @@ class SpaceCardData(CardData):
         super().__init__(**kwargs)
 
 
-def model_index_to_eval_results(model_index: List[Dict[str, Any]]) -> Tuple[str, List[EvalResult]]:
+def model_index_to_eval_results(model_index: list[dict[str, Any]]) -> tuple[str, list[EvalResult]]:
     """Takes in a model index and returns the model name and a list of `huggingface_hub.EvalResult` objects.
 
     A detailed spec of the model index can be found here:
     https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
 
     Args:
-        model_index (`List[Dict[str, Any]]`):
+        model_index (`list[dict[str, Any]]`):
             A model index data structure, likely coming from a README.md file on the
             Hugging Face Hub.
 
@@ -567,7 +567,7 @@ def model_index_to_eval_results(model_index: List[Dict[str, Any]]) -> Tuple[str,
         model_name (`str`):
             The name of the model as found in the model index. This is used as the
             identifier for the model on leaderboards like PapersWithCode.
-        eval_results (`List[EvalResult]`):
+        eval_results (`list[EvalResult]`):
             A list of `huggingface_hub.EvalResult` objects containing the metrics
             reported in the provided model_index.
 
@@ -668,7 +668,7 @@ def _remove_none(obj):
         return obj
 
 
-def eval_results_to_model_index(model_name: str, eval_results: List[EvalResult]) -> List[Dict[str, Any]]:
+def eval_results_to_model_index(model_name: str, eval_results: list[EvalResult]) -> list[dict[str, Any]]:
     """Takes in given model name and list of `huggingface_hub.EvalResult` and returns a
     valid model-index that will be compatible with the format expected by the
     Hugging Face Hub.
@@ -677,12 +677,12 @@ def eval_results_to_model_index(model_name: str, eval_results: List[EvalResult])
         model_name (`str`):
             Name of the model (ex. "my-cool-model"). This is used as the identifier
             for the model on leaderboards like PapersWithCode.
-        eval_results (`List[EvalResult]`):
+        eval_results (`list[EvalResult]`):
             List of `huggingface_hub.EvalResult` objects containing the metrics to be
             reported in the model-index.
 
     Returns:
-        model_index (`List[Dict[str, Any]]`): The eval_results converted to a model-index.
+        model_index (`list[dict[str, Any]]`): The eval_results converted to a model-index.
 
     Example:
         ```python
@@ -705,7 +705,7 @@ def eval_results_to_model_index(model_name: str, eval_results: List[EvalResult])
 
     # Metrics are reported on a unique task-and-dataset basis.
     # Here, we make a map of those pairs and the associated EvalResults.
-    task_and_ds_types_map: Dict[Any, List[EvalResult]] = defaultdict(list)
+    task_and_ds_types_map: dict[Any, list[EvalResult]] = defaultdict(list)
     for eval_result in eval_results:
         task_and_ds_types_map[eval_result.unique_identifier].append(eval_result)
 
@@ -760,7 +760,7 @@ def eval_results_to_model_index(model_name: str, eval_results: List[EvalResult])
     return _remove_none(model_index)
 
 
-def _to_unique_list(tags: Optional[List[str]]) -> Optional[List[str]]:
+def _to_unique_list(tags: Optional[list[str]]) -> Optional[list[str]]:
     if tags is None:
         return tags
     unique_tags = []  # make tags unique + keep order explicitly

huggingface_hub/serialization/__init__.py

@@ -15,7 +15,6 @@
 """Contains helpers to serialize tensors."""
 
 from ._base import StateDictSplit, split_state_dict_into_shards_factory
-from ._tensorflow import get_tf_storage_size, split_tf_state_dict_into_shards
 from ._torch import (
     get_torch_storage_id,
     get_torch_storage_size,

huggingface_hub/serialization/_base.py

@@ -14,7 +14,7 @@
 """Contains helpers to split tensors into shards."""
 
 from dataclasses import dataclass, field
-from typing import Any, Callable, Dict, List, Optional, TypeVar, Union
+from typing import Any, Callable, Optional, TypeVar, Union
 
 from .. import logging
 
@@ -38,16 +38,16 @@ logger = logging.get_logger(__file__)
 @dataclass
 class StateDictSplit:
     is_sharded: bool = field(init=False)
-    metadata: Dict[str, Any]
-    filename_to_tensors: Dict[str, List[str]]
-    tensor_to_filename: Dict[str, str]
+    metadata: dict[str, Any]
+    filename_to_tensors: dict[str, list[str]]
+    tensor_to_filename: dict[str, str]
 
     def __post_init__(self):
         self.is_sharded = len(self.filename_to_tensors) > 1
 
 
 def split_state_dict_into_shards_factory(
-    state_dict: Dict[str, TensorT],
+    state_dict: dict[str, TensorT],
     *,
     get_storage_size: TensorSizeFn_T,
     filename_pattern: str,
@@ -70,7 +70,7 @@ def split_state_dict_into_shards_factory(
     </Tip>
 
     Args:
-        state_dict (`Dict[str, Tensor]`):
+        state_dict (`dict[str, Tensor]`):
             The state dictionary to save.
         get_storage_size (`Callable[[Tensor], int]`):
             A function that returns the size of a tensor when saved on disk in bytes.
@@ -87,10 +87,10 @@ def split_state_dict_into_shards_factory(
     Returns:
         [`StateDictSplit`]: A `StateDictSplit` object containing the shards and the index to retrieve them.
     """
-    storage_id_to_tensors: Dict[Any, List[str]] = {}
+    storage_id_to_tensors: dict[Any, list[str]] = {}
 
-    shard_list: List[Dict[str, TensorT]] = []
-    current_shard: Dict[str, TensorT] = {}
+    shard_list: list[dict[str, TensorT]] = []
+    current_shard: dict[str, TensorT] = {}
     current_shard_size = 0
     total_size = 0