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

Tests: move generate tests to the right mixin and delete redundant tests (#34464)

Browse Source 
* tmp commit

* tmp commit

* cull overwrites of deleted tests

* typo

* more specific docstring

* make fixup

* parameterize at the top?

* correction

* more deletions :D

* tmp commit

* for VLMs too

* fix _check_outputs

* test nit

* make fixup

* fix another flaky

* test_generate_from_inputs_embeds -- handle missing attention mask
This commit is contained in:
Joao Gante
2024-10-30 10:59:08 +00:00
committed by GitHub
parent 913330ca9f
commit 8a734ea2c3
46 changed files with 265 additions and 2348 deletions
Download Patch File Download Diff File Expand all files Collapse all files

80
tests/models/starcoder2/test_modeling_starcoder2.py
View File

@@ -14,7 +14,6 @@
# limitations under the License.
"""Testing suite for the PyTorch Starcoder2 model."""
import tempfile
import unittest
import pytest
@@ -404,85 +403,6 @@ class Starcoder2ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTeste
def test_past_key_values_format(self):
pass
@require_flash_attn
@require_torch_gpu
@pytest.mark.flash_attn_test
@slow
def test_flash_attn_2_generate_padding_right(self):
import torch
for model_class in self.all_generative_model_classes:
config, _ = self.model_tester.prepare_config_and_inputs_for_common()
model = model_class(config)
with tempfile.TemporaryDirectory() as tmpdirname:
model.save_pretrained(tmpdirname)
model = model_class.from_pretrained(tmpdirname, torch_dtype=torch.float16, low_cpu_mem_usage=True).to(
torch_device
)
dummy_input = torch.LongTensor([[0, 2, 3, 4], [0, 2, 3, 4]]).to(torch_device)
dummy_attention_mask = torch.LongTensor([[1, 1, 1, 1], [1, 1, 1, 0]]).to(torch_device)
model.generate(dummy_input, attention_mask=dummy_attention_mask, max_new_tokens=1, do_sample=False)
model = model_class.from_pretrained(
tmpdirname,
torch_dtype=torch.float16,
attn_implementation="flash_attention_2",
low_cpu_mem_usage=True,
).to(torch_device)
with self.assertRaises(ValueError):
_ = model.generate(
dummy_input, attention_mask=dummy_attention_mask, max_new_tokens=1, do_sample=False
)
@require_flash_attn
@require_torch_gpu
@pytest.mark.flash_attn_test
@slow
def test_flash_attn_2_generate_use_cache(self):
import torch
max_new_tokens = 30
for model_class in self.all_generative_model_classes:
config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()
dummy_input = inputs_dict[model_class.main_input_name]
if dummy_input.dtype in [torch.float32, torch.bfloat16]:
dummy_input = dummy_input.to(torch.float16)
# make sure that all models have enough positions for generation
if hasattr(config, "max_position_embeddings"):
config.max_position_embeddings = max_new_tokens + dummy_input.shape[1] + 1
model = model_class(config)
with tempfile.TemporaryDirectory() as tmpdirname:
model.save_pretrained(tmpdirname)
dummy_attention_mask = inputs_dict.get("attention_mask", torch.ones_like(dummy_input))
# NOTE: Starcoder2 apparently does not support right padding + use_cache with FA2.
dummy_attention_mask[:, -1] = 1
model = model_class.from_pretrained(
tmpdirname,
torch_dtype=torch.float16,
attn_implementation="flash_attention_2",
low_cpu_mem_usage=True,
).to(torch_device)
# Just test that a large cache works as expected
_ = model.generate(
dummy_input,
attention_mask=dummy_attention_mask,
max_new_tokens=max_new_tokens,
do_sample=False,
use_cache=True,
)
@require_flash_attn
@require_torch_gpu
@pytest.mark.flash_attn_test