huggingface-hub 0.18.0rc0__py3-none-any.whl → 0.19.0__py3-none-any.whl

huggingface_hub/templates/datasetcard_template.md

@@ -1,103 +1,143 @@
 ---
-# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/datasetcard.md?plain=1
+# For reference on dataset card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/datasetcard.md?plain=1
 # Doc / guide: https://huggingface.co/docs/hub/datasets-cards
 {{ card_data }}
 ---
 
 # Dataset Card for {{ pretty_name | default("Dataset Name", true) }}
 
-## Dataset Description
+<!-- Provide a quick summary of the dataset. -->
 
-- **Homepage:** {{ homepage_url | default("", true)}}
-- **Repository:** {{ repo_url | default("", true)}}
-- **Paper:** {{ paper_url | default("", true)}}
-- **Leaderboard:** {{ leaderboard_url | default("", true)}}
-- **Point of Contact:** {{ point_of_contact | default("", true)}}
+{{ dataset_summary | default("", true) }}
 
-### Dataset Summary
+## Dataset Details
 
-{{ dataset_summary | default("[More Information Needed]", true)}}
+### Dataset Description
 
-### Supported Tasks and Leaderboards
+<!-- Provide a longer summary of what this dataset is. -->
 
-{{ supported_tasks_and_leaderboards_section | default("[More Information Needed]", true)}}
+{{ dataset_description | default("", true) }}
 
-### Languages
+- **Curated by:** {{ curators | default("[More Information Needed]", true)}}
+- **Funded by [optional]:** {{ funded_by | default("[More Information Needed]", true)}}
+- **Shared by [optional]:** {{ shared_by | default("[More Information Needed]", true)}}
+- **Language(s) (NLP):** {{ language | default("[More Information Needed]", true)}}
+- **License:** {{ license | default("[More Information Needed]", true)}}
 
-{{ languages_section | default("[More Information Needed]", true)}}
+### Dataset Sources [optional]
 
-## Dataset Structure
+<!-- Provide the basic links for the dataset. -->
+
+- **Repository:** {{ repo | default("[More Information Needed]", true)}}
+- **Paper [optional]:** {{ paper | default("[More Information Needed]", true)}}
+- **Demo [optional]:** {{ demo | default("[More Information Needed]", true)}}
+
+## Uses
 
-### Data Instances
+<!-- Address questions around how the dataset is intended to be used. -->
 
-{{ data_instances_section | default("[More Information Needed]", true)}}
+### Direct Use
 
-### Data Fields
+<!-- This section describes suitable use cases for the dataset. -->
 
-{{ data_fields_section | default("[More Information Needed]", true)}}
+{{ direct_use | default("[More Information Needed]", true)}}
 
-### Data Splits
+### Out-of-Scope Use
 
-{{ data_splits_section | default("[More Information Needed]", true)}}
+<!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. -->
+
+{{ out_of_scope_use | default("[More Information Needed]", true)}}
+
+## Dataset Structure
+
+<!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. -->
+
+{{ dataset_structure | default("[More Information Needed]", true)}}
 
 ## Dataset Creation
 
 ### Curation Rationale
 
+<!-- Motivation for the creation of this dataset. -->
+
 {{ curation_rationale_section | default("[More Information Needed]", true)}}
 
 ### Source Data
 
-#### Initial Data Collection and Normalization
+<!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). -->
+
+#### Data Collection and Processing
+
+<!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. -->
 
-{{ data_collection_section | default("[More Information Needed]", true)}}
+{{ data_collection_and_processing_section | default("[More Information Needed]", true)}}
 
-#### Who are the source language producers?
+#### Who are the source data producers?
 
-{{ source_language_producers_section | default("[More Information Needed]", true)}}
+<!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. -->
 
-### Annotations
+{{ source_data_producers_section | default("[More Information Needed]", true)}}
+
+### Annotations [optional]
+
+<!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. -->
 
 #### Annotation process
 
+<!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. -->
+
 {{ annotation_process_section | default("[More Information Needed]", true)}}
 
 #### Who are the annotators?
 
+<!-- This section describes the people or systems who created the annotations. -->
+
 {{ who_are_annotators_section | default("[More Information Needed]", true)}}
 
-### Personal and Sensitive Information
+#### Personal and Sensitive Information
+
+<!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. -->
+
+{{ personal_and_sensitive_information | default("[More Information Needed]", true)}}
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+{{ bias_risks_limitations | default("[More Information Needed]", true)}}
+
+### Recommendations
 
-{{ personal_and_sensitive_information_section | default("[More Information Needed]", true)}}
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
-## Considerations for Using the Data
+{{ bias_recommendations | default("Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.", true)}}
 
-### Social Impact of Dataset
+## Citation [optional]
 
-{{ social_impact_section | default("[More Information Needed]", true)}}
+<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
 
-### Discussion of Biases
+**BibTeX:**
 
-{{ discussion_of_biases_section | default("[More Information Needed]", true)}}
+{{ citation_bibtex | default("[More Information Needed]", true)}}
 
-### Other Known Limitations
+**APA:**
 
-{{ known_limitations_section | default("[More Information Needed]", true)}}
+{{ citation_apa | default("[More Information Needed]", true)}}
 
-## Additional Information
+## Glossary [optional]
 
-### Dataset Curators
+<!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. -->
 
-{{ dataset_curators_section | default("[More Information Needed]", true)}}
+{{ glossary | default("[More Information Needed]", true)}}
 
-### Licensing Information
+## More Information [optional]
 
-{{ licensing_information_section | default("[More Information Needed]", true)}}
+{{ more_information | default("[More Information Needed]", true)}}
 
-### Citation Information
+## Dataset Card Authors [optional]
 
-{{ citation_information_section | default("[More Information Needed]", true)}}
+{{ dataset_card_authors | default("[More Information Needed]", true)}}
 
-### Contributions
+## Dataset Card Contact
 
-{{ contributions_section | default("[More Information Needed]", true)}}
+{{ dataset_card_contact | default("[More Information Needed]", true)}}

huggingface_hub/templates/modelcard_template.md

@@ -19,11 +19,12 @@
 {{ model_description | default("", true) }}
 
 - **Developed by:** {{ developers | default("[More Information Needed]", true)}}
+- **Funded by [optional]:** {{ funded_by | default("[More Information Needed]", true)}}
 - **Shared by [optional]:** {{ shared_by | default("[More Information Needed]", true)}}
 - **Model type:** {{ model_type | default("[More Information Needed]", true)}}
 - **Language(s) (NLP):** {{ language | default("[More Information Needed]", true)}}
 - **License:** {{ license | default("[More Information Needed]", true)}}
-- **Finetuned from model [optional]:** {{ finetuned_from | default("[More Information Needed]", true)}}
+- **Finetuned from model [optional]:** {{ base_model | default("[More Information Needed]", true)}}
 
 ### Model Sources [optional]
 
@@ -77,7 +78,7 @@ Use the code below to get started with the model.
 
 ### 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. -->
+<!-- This should link to a Dataset 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)}}
 
@@ -108,7 +109,7 @@ Use the code below to get started with the model.
 
 #### Testing Data
 
-<!-- This should link to a Data Card if possible. -->
+<!-- This should link to a Dataset Card if possible. -->
 
 {{ testing_data | default("[More Information Needed]", true)}}
 

huggingface_hub/utils/__init__.py

@@ -44,7 +44,7 @@ from ._fixes import SoftTemporaryDirectory, yaml_dump
 from ._git_credential import list_credential_helpers, set_git_credential, unset_git_credential
 from ._headers import build_hf_headers, get_token_to_send, LocalTokenNotFoundError
 from ._hf_folder import HfFolder
-from ._http import configure_http_backend, get_session, http_backoff
+from ._http import configure_http_backend, get_session, http_backoff, reset_sessions
 from ._pagination import paginate
 from ._paths import filter_repo_objects, IGNORE_GIT_FOLDER_PATTERNS
 from ._experimental import experimental

huggingface_hub/utils/_cache_assets.py

@@ -15,7 +15,7 @@
 from pathlib import Path
 from typing import Union
 
-from ..constants import HUGGINGFACE_ASSETS_CACHE
+from ..constants import HF_ASSETS_CACHE
 
 
 def cached_assets_path(
@@ -91,7 +91,7 @@ def cached_assets_path(
         assets_dir (`str`, `Path`, *optional*):
             Path to the folder where assets are cached. This must not be the same folder
             where Hub files are cached. Defaults to `HF_HOME / "assets"` if not provided.
-            Can also be set with `HUGGINGFACE_ASSETS_CACHE` environment variable.
+            Can also be set with `HF_ASSETS_CACHE` environment variable.
 
     Returns:
         Path to the cache folder (`Path`).
@@ -115,7 +115,7 @@ def cached_assets_path(
     """
     # Resolve assets_dir
     if assets_dir is None:
-        assets_dir = HUGGINGFACE_ASSETS_CACHE
+        assets_dir = HF_ASSETS_CACHE
     assets_dir = Path(assets_dir).expanduser().resolve()
 
     # Avoid names that could create path issues

huggingface_hub/utils/_cache_manager.py

@@ -21,7 +21,7 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Dict, FrozenSet, List, Literal, Optional, Set, Union
 
-from ..constants import HUGGINGFACE_HUB_CACHE
+from ..constants import HF_HUB_CACHE
 from . import logging
 
 
@@ -580,26 +580,25 @@ def scan_cache_dir(cache_dir: Optional[Union[str, Path]] = None) -> HFCacheInfo:
     Returns: a [`~HFCacheInfo`] object.
     """
     if cache_dir is None:
-        cache_dir = HUGGINGFACE_HUB_CACHE
+        cache_dir = HF_HUB_CACHE
 
     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 `HF_HUB_CACHE` environment variable.",
             cache_dir=cache_dir,
         )
 
     if cache_dir.is_file():
         raise ValueError(
-            f"Scan cache expects a directory but found a file: {cache_dir}. Please use"
-            " `cache_dir` argument or set `HUGGINGFACE_HUB_CACHE` environment"
-            " variable."
+            f"Scan cache expects a directory but found a file: {cache_dir}. Please use `cache_dir` argument or set `HF_HUB_CACHE` environment variable."
         )
 
     repos: Set[CachedRepoInfo] = set()
     warnings: List[CorruptedCacheException] = []
     for repo_path in cache_dir.iterdir():
+        if repo_path.name == ".locks":  # skip './.locks/' folder
+            continue
         try:
             repos.add(_scan_cached_repo(repo_path))
         except CorruptedCacheException as e:

huggingface_hub/utils/_datetime.py

@@ -55,7 +55,9 @@ def parse_datetime(date_string: str) -> datetime:
         # timezone and then move it to the appropriate UTC timezone.
         # See https://en.wikipedia.org/wiki/ISO_8601#Coordinated_Universal_Time_(UTC)
         # Taken from https://stackoverflow.com/a/3168394.
-
+        if len(date_string) == 30:
+            # Means timezoned-timestamp with nanoseconds precision. We need to truncate the last 3 digits.
+            date_string = date_string[:-4] + "Z"
         dt = datetime.strptime(date_string, "%Y-%m-%dT%H:%M:%S.%fZ")
         dt += UTC_OFFSET  # By default, datetime is not timezoned -> move to UTC time
         return dt.astimezone(timezone.utc)  # Set explicit timezone

huggingface_hub/utils/_errors.py

@@ -2,6 +2,7 @@ from typing import Optional
 
 from requests import HTTPError, Response
 
+from ..constants import INFERENCE_ENDPOINTS_ENDPOINT
 from ._fixes import JSONDecodeError
 
 
@@ -293,6 +294,15 @@ def hf_raise_for_status(response: Response, endpoint_name: Optional[str] = None)
             # This prevent from raising a misleading `RepositoryNotFoundError` (see below).
             pass
 
+        elif (
+            response.status_code == 401
+            and response.request.url is not None
+            and INFERENCE_ENDPOINTS_ENDPOINT in response.request.url
+        ):
+            # Not enough permission to list Inference Endpoints from this org. We don't raise a custom error for this.
+            # This prevent from raising a misleading `RepositoryNotFoundError` (see below).
+            pass
+
         elif error_code == "RepoNotFound" or response.status_code == 401:
             # 401 is misleading as it is returned for:
             #    - private and gated repos if user is not authenticated

huggingface_hub/utils/_hf_folder.py

@@ -46,7 +46,7 @@ class HfFolder:
         """
         Get token or None if not existent.
 
-        Note that a token can be also provided using the `HUGGING_FACE_HUB_TOKEN` environment variable.
+        Note that a token can be also provided using the `HF_TOKEN` environment variable.
 
         Token is saved in the huggingface home folder. You can configure it by setting
         the `HF_HOME` environment variable. Previous location was `~/.huggingface/token`.
@@ -63,7 +63,9 @@ class HfFolder:
             pass
 
         # 1. Is it set by environment variable ?
-        token: Optional[str] = os.environ.get("HUGGING_FACE_HUB_TOKEN")
+        token: Optional[str] = os.environ.get("HF_TOKEN")
+        if token is None:  # Ensure backward compatibility but doesn't have priority
+            token = os.environ.get("HUGGING_FACE_HUB_TOKEN")
         if token is not None:
             token = token.replace("\r", "").replace("\n", "").strip()
             return token

huggingface_hub/utils/_http.py

@@ -113,7 +113,7 @@ def configure_http_backend(backend_factory: BACKEND_FACTORY_T = _default_backend
     """
     global _GLOBAL_BACKEND_FACTORY
     _GLOBAL_BACKEND_FACTORY = backend_factory
-    _get_session_from_cache.cache_clear()
+    reset_sessions()
 
 
 def get_session() -> requests.Session:
@@ -148,6 +148,15 @@ def get_session() -> requests.Session:
     return _get_session_from_cache(process_id=os.getpid(), thread_id=threading.get_ident())
 
 
+def reset_sessions() -> None:
+    """Reset the cache of sessions.
+
+    Mostly used internally when sessions are reconfigured or an SSLError is raised.
+    See [`configure_http_backend`] for more details.
+    """
+    _get_session_from_cache.cache_clear()
+
+
 @lru_cache
 def _get_session_from_cache(process_id: int, thread_id: int) -> requests.Session:
     """

huggingface_hub/utils/_runtime.py

@@ -305,8 +305,8 @@ def dump_environment_info() -> Dict[str, Any]:
 
     # Environment variables
     info["ENDPOINT"] = constants.ENDPOINT
-    info["HUGGINGFACE_HUB_CACHE"] = constants.HUGGINGFACE_HUB_CACHE
-    info["HUGGINGFACE_ASSETS_CACHE"] = constants.HUGGINGFACE_ASSETS_CACHE
+    info["HF_HUB_CACHE"] = constants.HF_HUB_CACHE
+    info["HF_ASSETS_CACHE"] = constants.HF_ASSETS_CACHE
     info["HF_TOKEN_PATH"] = constants.HF_TOKEN_PATH
     info["HF_HUB_OFFLINE"] = constants.HF_HUB_OFFLINE
     info["HF_HUB_DISABLE_TELEMETRY"] = constants.HF_HUB_DISABLE_TELEMETRY
@@ -315,6 +315,8 @@ def dump_environment_info() -> Dict[str, Any]:
     info["HF_HUB_DISABLE_EXPERIMENTAL_WARNING"] = constants.HF_HUB_DISABLE_EXPERIMENTAL_WARNING
     info["HF_HUB_DISABLE_IMPLICIT_TOKEN"] = constants.HF_HUB_DISABLE_IMPLICIT_TOKEN
     info["HF_HUB_ENABLE_HF_TRANSFER"] = constants.HF_HUB_ENABLE_HF_TRANSFER
+    info["HF_HUB_ETAG_TIMEOUT"] = constants.HF_HUB_ETAG_TIMEOUT
+    info["HF_HUB_DOWNLOAD_TIMEOUT"] = constants.HF_HUB_DOWNLOAD_TIMEOUT
 
     print("\nCopy-and-paste the text below in your GitHub issue.\n")
     print("\n".join([f"- {prop}: {val}" for prop, val in info.items()]) + "\n")

huggingface_hub/utils/endpoint_helpers.py

@@ -16,27 +16,28 @@ with the aim for a user-friendly interface.
 import math
 import re
 from dataclasses import dataclass
-from typing import TYPE_CHECKING, Iterable, List, Optional, Union
+from typing import TYPE_CHECKING, List, Optional, Union
+
+from ..repocard_data import ModelCardData
 
 
 if TYPE_CHECKING:
     from ..hf_api import ModelInfo
 
 
-def _filter_emissions(
-    models: Iterable["ModelInfo"],
-    minimum_threshold: Optional[float] = None,
-    maximum_threshold: Optional[float] = None,
-) -> Iterable["ModelInfo"]:
-    """Filters a list of models for those that include an emission tag and limit them to between two thresholds
+def _is_emission_within_treshold(model_info: "ModelInfo", minimum_threshold: float, maximum_threshold: float) -> bool:
+    """Checks if a model's emission is within a given threshold.
 
     Args:
-        models (Iterable of `ModelInfo`):
-            A list of models to filter.
-        minimum_threshold (`float`, *optional*):
+        model_info (`ModelInfo`):
+            A model info object containing the model's emission information.
+        minimum_threshold (`float`):
             A minimum carbon threshold to filter by, such as 1.
-        maximum_threshold (`float`, *optional*):
+        maximum_threshold (`float`):
             A maximum carbon threshold to filter by, such as 10.
+
+    Returns:
+        `bool`: Whether the model's emission is within the given threshold.
     """
     if minimum_threshold is None and maximum_threshold is None:
         raise ValueError("Both `minimum_threshold` and `maximum_threshold` cannot both be `None`")
@@ -45,26 +46,24 @@ def _filter_emissions(
     if maximum_threshold is None:
         maximum_threshold = math.inf
 
-    for model in models:
-        card_data = getattr(model, "cardData", None)
-        if card_data is None or not isinstance(card_data, dict):
-            continue
+    card_data = getattr(model_info, "card_data", None)
+    if card_data is None or not isinstance(card_data, (dict, ModelCardData)):
+        return False
 
-        # Get CO2 emission metadata
-        emission = card_data.get("co2_eq_emissions", None)
-        if isinstance(emission, dict):
-            emission = emission["emissions"]
-        if not emission:
-            continue
+    # Get CO2 emission metadata
+    emission = card_data.get("co2_eq_emissions", None)
+    if isinstance(emission, dict):
+        emission = emission["emissions"]
+    if not emission:
+        return False
 
-        # Filter out if value is missing or out of range
-        matched = re.search(r"\d+\.\d+|\d+", str(emission))
-        if matched is None:
-            continue
+    # Filter out if value is missing or out of range
+    matched = re.search(r"\d+\.\d+|\d+", str(emission))
+    if matched is None:
+        return False
 
-        emission_value = float(matched.group(0))
-        if emission_value >= minimum_threshold and emission_value <= maximum_threshold:
-            yield model
+    emission_value = float(matched.group(0))
+    return minimum_threshold <= emission_value <= maximum_threshold
 
 
 @dataclass
@@ -203,16 +202,11 @@ class ModelFilter:
     >>> # For the task
     >>> new_filter = ModelFilter(task="text-classification")
 
-    >>> # Retrieving tags using the `HfApi.get_model_tags` method
     >>> from huggingface_hub import HfApi
 
     >>> api = HfApi()
     # To list model tags
 
-    >>> api.get_model_tags()
-    # To list dataset tags
-
-    >>> api.get_dataset_tags()
     >>> new_filter = ModelFilter(tags="benchmark:raft")
 
     >>> # Related to the dataset
@@ -227,145 +221,3 @@ class ModelFilter:
     task: Optional[Union[str, List[str]]] = None
     trained_dataset: Optional[Union[str, List[str]]] = None
     tags: Optional[Union[str, List[str]]] = None
-
-
-class AttributeDictionary(dict):
-    """
-    `dict` subclass that also provides access to keys as attributes
-
-    If a key starts with a number, it will exist in the dictionary but not as an
-    attribute
-
-    Example:
-
-    ```python
-    >>> d = AttributeDictionary()
-    >>> d["test"] = "a"
-    >>> print(d.test)  # prints "a"
-    ```
-
-    """
-
-    def __getattr__(self, k):
-        if k in self:
-            return self[k]
-        else:
-            raise AttributeError(k)
-
-    def __setattr__(self, k, v):
-        (self.__setitem__, super().__setattr__)[k[0] == "_"](k, v)
-
-    def __delattr__(self, k):
-        if k in self:
-            del self[k]
-        else:
-            raise AttributeError(k)
-
-    def __dir__(self):
-        keys = sorted(self.keys())
-        keys = [key for key in keys if key.replace("_", "").isalpha()]
-        return super().__dir__() + keys
-
-    def __repr__(self):
-        repr_str = "Available Attributes or Keys:\n"
-        for key in sorted(self.keys()):
-            repr_str += f" * {key}"
-            if not key.replace("_", "").isalpha():
-                repr_str += " (Key only)"
-            repr_str += "\n"
-        return repr_str
-
-
-class GeneralTags(AttributeDictionary):
-    """
-    A namespace object holding all tags, filtered by `keys` If a tag starts with
-    a number, it will only exist in the dictionary
-
-    Example:
-    ```python
-    >>> a.b["1a"]  # will work
-    >>> a["b"]["1a"]  # will work
-    >>> # a.b.1a # will not work
-    ```
-
-    Args:
-        tag_dictionary (`dict`):
-            A dictionary of tags returned from the /api/***-tags-by-type api
-            endpoint
-        keys (`list`):
-            A list of keys to unpack the `tag_dictionary` with, such as
-            `["library","language"]`
-    """
-
-    def __init__(self, tag_dictionary: dict, keys: Optional[list] = None):
-        self._tag_dictionary = tag_dictionary
-        if keys is None:
-            keys = list(self._tag_dictionary.keys())
-        for key in keys:
-            self._unpack_and_assign_dictionary(key)
-
-    def _unpack_and_assign_dictionary(self, key: str):
-        "Assign nested attributes to `self.key` containing information as an `AttributeDictionary`"
-        ref = AttributeDictionary()
-        setattr(self, key, ref)
-        for item in self._tag_dictionary.get(key, []):
-            label = item["label"].replace(" ", "").replace("-", "_").replace(".", "_")
-            ref[label] = item["id"]
-        self[key] = ref
-
-
-class ModelTags(GeneralTags):
-    """
-    A namespace object holding all available model tags If a tag starts with a
-    number, it will only exist in the dictionary
-
-    Example:
-
-    ```python
-    >>> a.dataset["1_5BArabicCorpus"]  # will work
-    >>> a["dataset"]["1_5BArabicCorpus"]  # will work
-    >>> # o.dataset.1_5BArabicCorpus # will not work
-    ```
-
-    Args:
-        model_tag_dictionary (`dict`):
-            A dictionary of valid model tags, returned from the
-            /api/models-tags-by-type api endpoint
-    """
-
-    def __init__(self, model_tag_dictionary: dict):
-        keys = ["library", "language", "license", "dataset", "pipeline_tag"]
-        super().__init__(model_tag_dictionary, keys)
-
-
-class DatasetTags(GeneralTags):
-    """
-    A namespace object holding all available dataset tags If a tag starts with a
-    number, it will only exist in the dictionary
-
-    Example
-
-    ```python
-    >>> a.size_categories["100K<n<1M"]  # will work
-    >>> a["size_categories"]["100K<n<1M"]  # will work
-    >>> # o.size_categories.100K<n<1M # will not work
-    ```
-
-    Args:
-        dataset_tag_dictionary (`dict`):
-            A dictionary of valid dataset tags, returned from the
-            /api/datasets-tags-by-type api endpoint
-    """
-
-    def __init__(self, dataset_tag_dictionary: dict):
-        keys = [
-            "language",
-            "multilinguality",
-            "language_creators",
-            "task_categories",
-            "size_categories",
-            "benchmark",
-            "task_ids",
-            "license",
-        ]
-        super().__init__(dataset_tag_dictionary, keys)