Replace ReprMixin with dataclasses (#1788)

* Define dataclasses

* Update docs

* Update tests

* Fixes

* Remove InitVar

* Style

* Apply suggestions from code review

Co-authored-by: Lucain <lucainp@gmail.com>

---------

Co-authored-by: Lucain <lucainp@gmail.com>

docs/source/de/guides/search.md

@@ -52,11 +52,15 @@ Während des Filterns können Sie auch die Modelle sortieren und nur die Top-Erg
 Zum Beispiel holt das folgende Beispiel die 5 am häufigsten heruntergeladenen Datensätze auf dem Hub:
 
 ```py
->>> list_datasets(sort="downloads", direction=-1, limit=5)
-[DatasetInfo: {
-        id: glue
-		downloads: 897789
-		(...)
+>>> list(list_datasets(sort="downloads", direction=-1, limit=5))
+[DatasetInfo(
+	id='argilla/databricks-dolly-15k-curated-en',
+	author='argilla',
+	sha='4dcd1dedbe148307a833c931b21ca456a1fc4281', 
+	last_modified=datetime.datetime(2023, 10, 2, 12, 32, 53, tzinfo=datetime.timezone.utc), 
+	private=False,
+	downloads=8889377,
+	(...)
 ```
 
 

docs/source/en/guides/collections.md

@@ -22,30 +22,26 @@ Let's fetch the collection with, `"TheBloke/recent-models-64f9a55bb3115b4f513ec0
 >>> from huggingface_hub import get_collection
 >>> collection = get_collection("TheBloke/recent-models-64f9a55bb3115b4f513ec026")
 >>> collection
-Collection: { 
-  {'description': "Models I've recently quantized.',
-   'items': [...],
-   'last_updated': datetime.datetime(2023, 9, 21, 7, 26, 28, 57000, tzinfo=datetime.timezone.utc),
-   'owner': 'TheBloke',
-   'position': 1,
-   'private': False,
-   'slug': 'TheBloke/recent-models-64f9a55bb3115b4f513ec026',
-   'theme': 'green',
-   'title': 'Recent models'}
-}
+Collection(
+  slug='TheBloke/recent-models-64f9a55bb3115b4f513ec026',
+  title='Recent models',
+  owner='TheBloke',
+  items=[...],
+  last_updated=datetime.datetime(2023, 10, 2, 22, 56, 48, 632000, tzinfo=datetime.timezone.utc),
+  position=1,
+  private=False,
+  theme='green',
+  upvotes=90,
+  description="Models I've recently quantized. Please note that currently this list has to be updated manually, and therefore is not guaranteed to be up-to-date."
+)
 >>> collection.items[0]
-CollectionItem: { 
-  {'item_object_id': '6507f6d5423b46492ee1413e',
-   'author': 'TheBloke',
-   'item_id': 'TheBloke/TigerBot-70B-Chat-GPTQ',
-   'item_type': 'model',
-   'lastModified': '2023-09-19T12:55:21.000Z',
-   'position': 0,
-   'private': False,
-   'repoType': 'model'
-   (...)
-  }
-}
+CollectionItem(
+  item_object_id='651446103cd773a050bf64c2',
+  item_id='TheBloke/U-Amethyst-20B-AWQ',
+  item_type='model',
+  position=88, 
+  note=None
+)
 ```
 
 The [`Collection`] object returned by [`get_collection`] contains:

docs/source/en/guides/search.md

@@ -52,11 +52,15 @@ While filtering, you can also sort the models and take only the top results. For
 the following example fetches the top 5 most downloaded datasets on the Hub:
 
 ```py
->>> list_datasets(sort="downloads", direction=-1, limit=5)
-[DatasetInfo: {
-        id: glue
-		downloads: 897789
-		(...)
+>>> list(list_datasets(sort="downloads", direction=-1, limit=5))
+[DatasetInfo(
+	id='argilla/databricks-dolly-15k-curated-en',
+	author='argilla',
+	sha='4dcd1dedbe148307a833c931b21ca456a1fc4281', 
+	last_modified=datetime.datetime(2023, 10, 2, 12, 32, 53, tzinfo=datetime.timezone.utc), 
+	private=False,
+	downloads=8889377,
+	(...)
 ```
 
 

docs/source/en/package_reference/hf_api.md

@@ -59,6 +59,10 @@ models = hf_api.list_models()
 
 [[autodoc]] huggingface_hub.hf_api.ModelInfo
 
+### RepoSibling
+
+[[autodoc]] huggingface_hub.hf_api.RepoSibling
+
 ### RepoFile
 
 [[autodoc]] huggingface_hub.hf_api.RepoFile

src/huggingface_hub/_snapshot_download.py

@@ -189,6 +189,7 @@ def snapshot_download(
     api = HfApi(library_name=library_name, library_version=library_version, user_agent=user_agent, endpoint=endpoint)
     repo_info = api.repo_info(repo_id=repo_id, repo_type=repo_type, revision=revision, token=token)
     assert repo_info.sha is not None, "Repo info returned from server must have a revision sha."
+    assert repo_info.siblings is not None, "Repo info returned from server must have a siblings list."
 
     filtered_repo_files = list(
         filter_repo_objects(

src/huggingface_hub/_tensorboard_logger.py

@@ -24,6 +24,7 @@
     from tensorboardX import SummaryWriter
 
     # TODO: clarify: should we import from torch.utils.tensorboard ?
+
 else:
     SummaryWriter = object  # Dummy class to avoid failing at import. Will raise on instance creation.
 

src/huggingface_hub/constants.py

@@ -5,6 +5,7 @@
 
 # Possible values for env variables
 
+
 ENV_VARS_TRUE_VALUES = {"1", "ON", "YES", "TRUE"}
 ENV_VARS_TRUE_AND_AUTO_VALUES = ENV_VARS_TRUE_VALUES.union({"AUTO"})