Remove static pretrained maps from the library's internals (#29112)

* [test_all] Remove static pretrained maps from the library's internals

* Deprecate archive maps instead of removing them

* Revert init changes

* [test_all] Deprecate instead of removing

* [test_all] PVT v2 support

* [test_all] Tests should all pass

* [test_all] Style

* Address review comments

* Update src/transformers/models/deprecated/_archive_maps.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update src/transformers/models/deprecated/_archive_maps.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* [test_all] trigger tests

* [test_all] LLAVA

* [test_all] Bad rebase

---------

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
This commit is contained in:
Lysandre Debut
2024-03-25 10:33:38 +01:00
committed by GitHub
parent 76a33a1092
commit 39114c0383
842 changed files with 4608 additions and 8613 deletions

View File

@@ -348,14 +348,6 @@ class SiglipTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
special_tokens_string_rust = rust_tokenizer.convert_tokens_to_string(special_tokens)
self.assertEqual(special_tokens_string, special_tokens_string_rust)
# overwritten from `test_tokenization_common` since Siglip has no max length
# Copied from tests.models.t5.test_tokenization_t5.T5TokenizationTest.test_pretrained_model_lists with T5->Siglip
def test_pretrained_model_lists(self):
# We should have at least one default checkpoint for each tokenizer
# We should specify the max input length as well (used in some part to list the pretrained checkpoints)
self.assertGreaterEqual(len(self.tokenizer_class.pretrained_vocab_files_map), 1)
self.assertGreaterEqual(len(list(self.tokenizer_class.pretrained_vocab_files_map.values())[0]), 1)
@slow
def test_tokenizer_integration(self):
tokenizer = SiglipTokenizer.from_pretrained("google/siglip-base-patch16-224")