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

CI: AMD MI300 tests fix (#30797)

Browse Source 
* add fix

* update import

* updated dicts and comments

* remove prints

* Update testing_utils.py
This commit is contained in:
Mohit Sharma
2024-05-21 17:16:07 +05:30
committed by GitHub
parent a755745546
commit 7a4792e6b3
10 changed files with 126 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
tests/models/mistral/test_modeling_mistral.py
View File

@@ -520,12 +520,16 @@ class MistralIntegrationTest(unittest.TestCase):
EXPECTED_MEAN = torch.tensor([[-2.5548, -2.5737, -3.0600, -2.5906, -2.8478, -2.8118, -2.9325, -2.7694]])
torch.testing.assert_close(out.mean(-1), EXPECTED_MEAN, atol=1e-2, rtol=1e-2)
# Key 9 for MI300, Key 8 for A100/A10, and Key 7 for T4.
#
# Note: Key 9 is currently set for MI300, but may need potential future adjustments for H100s,
# considering differences in hardware processing and potential deviations in output.
EXPECTED_SLICE = {
7: torch.tensor([-5.8781, -5.8616, -0.1052, -4.7200, -5.8781, -5.8774, -5.8773, -5.8777, -5.8781, -5.8780, -5.8781, -5.8779, -1.0787, 1.7583, -5.8779, -5.8780, -5.8783, -5.8778, -5.8776, -5.8781, -5.8784, -5.8778, -5.8778, -5.8777, -5.8779, -5.8778, -5.8776, -5.8780, -5.8779, -5.8781]),
8: torch.tensor([-5.8711, -5.8555, -0.1050, -4.7148, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -1.0781, 1.7568, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711, -5.8711]),
9: torch.tensor([-5.8750, -5.8594, -0.1047, -4.7188, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -1.0781, 1.7578, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750, -5.8750]),
} # fmt: skip
print(out[0, 0, :30])
torch.testing.assert_close(
out[0, 0, :30], EXPECTED_SLICE[self.cuda_compute_capability_major_version], atol=1e-4, rtol=1e-4
)
@@ -625,9 +629,14 @@ class MistralIntegrationTest(unittest.TestCase):
@slow
def test_speculative_generation(self):
# Key 9 for MI300, Key 8 for A100/A10, and Key 7 for T4.
#
# Note: Key 9 is currently set for MI300, but may need potential future adjustments for H100s,
# considering differences in hardware processing and potential deviations in generated text.
EXPECTED_TEXT_COMPLETION = {
7: "My favourite condiment is 100% Sriracha. I love the heat, the tang and the fact costs",
8: "My favourite condiment is 100% ketchup. I love it on everything. I’m not a big",
9: "My favourite condiment is 100% ketchup. I love it on everything. I’m not a big",
}
prompt = "My favourite condiment is "
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1", use_fast=False)