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

VLMs: enable generation tests (#33533)

Browse Source 
* add tests

* fix whisper

* update

* nit

* add qwen2-vl

* more updates!

* better this way

* fix this one

* fix more tests

* fix final tests, hope so

* fix led

* Update tests/generation/test_utils.py

Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com>

* pr comments

* not pass pixels and extra for low-mem tests, very flaky because of visio tower

---------

Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com>
This commit is contained in:
Raushan Turganbay
2024-09-19 12:04:24 +02:00
committed by GitHub
parent e40bb4845e
commit d7975a5874
22 changed files with 500 additions and 207 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/models/speech_to_text/test_modeling_speech_to_text.py
View File

@@ -285,7 +285,7 @@ class Speech2TextModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTest
input_name = "input_features"
def _get_input_ids_and_config(self, batch_size=2):
config, input_ids, attention_mask = GenerationTesterMixin._get_input_ids_and_config(self)
config, input_ids, attention_mask, inputs_dict = GenerationTesterMixin._get_input_ids_and_config(self)
# `input_ids` is actually `input_features` which is a 3D tensor.
# We must overwrite the mask to make it 2D since the original `_get_input_ids_and_config` creates an
@@ -294,7 +294,7 @@ class Speech2TextModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTest
sequence_length = input_ids.shape[1]
attention_mask = torch.ones((batch_size, sequence_length), dtype=torch.long, device=attention_mask.device)
return config, input_ids, attention_mask
return config, input_ids, attention_mask, inputs_dict
def setUp(self):
self.model_tester = Speech2TextModelTester(self)