riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-03 12:50:06 +06:00
Code Issues Actions 28 Packages Projects Releases Wiki Activity

Fix deepseekv3 (#38562)

Browse Source 
* fix 1

* fix 2

* fix 3

* fix 4

* update

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
Yih-Dar 2025-06-04 11:40:14 +02:00 committed by GitHub
parent 6085cded38
commit ff3fad61e3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
tests/models/deepseek_v3/test_modeling_deepseek_v3.py
View File

@ -24,6 +24,7 @@ from transformers.testing_utils import (
require_read_token, require_read_token,
require_torch, require_torch,
require_torch_accelerator, require_torch_accelerator,
require_torch_large_accelerator,
require_torch_sdpa, require_torch_sdpa,
slow, slow,
torch_device, torch_device,
@ -443,6 +444,7 @@ class DeepseekV3ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTeste
] ]
super().test_past_key_values_format(custom_all_cache_shapes=all_cache_shapes) super().test_past_key_values_format(custom_all_cache_shapes=all_cache_shapes)
@require_torch_large_accelerator
@require_torch_sdpa @require_torch_sdpa
@slow @slow
def test_eager_matches_sdpa_generate(self): def test_eager_matches_sdpa_generate(self):
@ -509,14 +511,12 @@ class DeepseekV3IntegrationTest(unittest.TestCase):
self.skipTest(reason="This test requires torch >= 2.3 to run.") self.skipTest(reason="This test requires torch >= 2.3 to run.")
NUM_TOKENS_TO_GENERATE = 40 NUM_TOKENS_TO_GENERATE = 40
# Note on `EXPECTED_TEXT_COMPLETION`'s diff: the current value matches the original test if the original test # https://github.com/huggingface/transformers/pull/38562#issuecomment-2939209171
# was changed to have a cache of 53 tokens (as opposed to 4096), on Ampere GPUs. # The reason why the output is gibberish is because the testing model bzantium/tiny-deepseek-v3 is not trained
# one. Since original DeepSeek-V3 model is too big to debug and test, there was no testing with the original one.
EXPECTED_TEXT_COMPLETION = [ EXPECTED_TEXT_COMPLETION = [
"Simply put, the theory of relativity states that 1) the speed of light is constant in all inertial " "Simply put, the theory of relativity states that Frojekecdytesాలు sicʰtinaccianntuala breej的效率和质量的控制lavestock-PraccuraciesOTTensorialoghismos的思路astiomotivityosexualriad TherapeuticsoldtYPEface Kishsatellite-TV",
"reference frames, and 2) the laws of physics are the same for all inertial reference frames.\nThe " "My favorite all time favorite condiment is ketchup.ieden沟渠係室温 Fryrok般地Segmentation Cycle/physicalwarenkrautempsాలు蹈梗 Mesomac一等asan lethality suspended Causewaydreamswith Fossilsdorfాలు蹈 ChristiansenHOMEbrew",
"theory of relativ",
"My favorite all time favorite condiment is ketchup. I love it on everything. I love it on my eggs, "
"my fries, my chicken, my burgers, my hot dogs, my sandwiches, my salads, my p",
] ]
prompts = [ prompts = [