SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

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

Browse Source 
* [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
Download Patch File Download Diff File Expand all files Collapse all files

7
tests/models/bloom/test_modeling_bloom.py
View File

@@ -30,7 +30,6 @@ if is_torch_available():
import torch
from transformers import (
BLOOM_PRETRAINED_MODEL_ARCHIVE_LIST,
BloomForCausalLM,
BloomForQuestionAnswering,
BloomForSequenceClassification,
@@ -396,9 +395,9 @@ class BloomModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixi
@slow
def test_model_from_pretrained(self):
for model_name in BLOOM_PRETRAINED_MODEL_ARCHIVE_LIST[:1]:
model = BloomModel.from_pretrained(model_name)
self.assertIsNotNone(model)
model_name = "bigscience/bigscience-small-testing"
model = BloomModel.from_pretrained(model_name)
self.assertIsNotNone(model)
@slow
@require_torch_accelerator

7
tests/models/bloom/test_tokenization_bloom.py
View File

@@ -132,13 +132,6 @@ class BloomTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
predicted_text = [tokenizer.decode(x, clean_up_tokenization_spaces=False) for x in output_tokens]
self.assertListEqual(predicted_text, input_text)
def test_pretrained_model_lists(self):
# The test has to be overriden because BLOOM uses ALiBi positional embeddings that does not have
# any sequence length constraints. This test of the parent class will fail since it relies on the
# maximum sequence length of the positoonal embeddings.
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)
@require_jinja
def test_tokenization_for_chat(self):
tokenizer = self.get_rust_tokenizer()