Skip to content

[LLM] Update model convert and fix TP for deepseekv3 #9797

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Jan 24, 2025

add deepseek-R1

a0f0535
Select commit
Loading
Failed to load commit list.
Merged

[LLM] Update model convert and fix TP for deepseekv3 #9797

add deepseek-R1
a0f0535
Select commit
Loading
Failed to load commit list.
Codecov / codecov/patch failed Jan 24, 2025 in 0s

4.16% of diff hit (target 80.00%)

View this Pull Request on Codecov

4.16% of diff hit (target 80.00%)

Annotations

Check warning on line 1315 in paddlenlp/transformers/conversion_utils.py

See this annotation in the file changed.

@codecov codecov / codecov/patch

paddlenlp/transformers/conversion_utils.py#L1315

Added line #L1315 was not covered by tests

Check warning on line 1322 in paddlenlp/transformers/conversion_utils.py

See this annotation in the file changed.

@codecov codecov / codecov/patch

paddlenlp/transformers/conversion_utils.py#L1322

Added line #L1322 was not covered by tests

Check warning on line 583 in paddlenlp/transformers/deepseek_v2/modeling.py

See this annotation in the file changed.

@codecov codecov / codecov/patch

paddlenlp/transformers/deepseek_v2/modeling.py#L583

Added line #L583 was not covered by tests

Check warning on line 763 in paddlenlp/transformers/deepseek_v2/modeling.py

See this annotation in the file changed.

@codecov codecov / codecov/patch

paddlenlp/transformers/deepseek_v2/modeling.py#L763

Added line #L763 was not covered by tests

Check warning on line 1162 in paddlenlp/transformers/deepseek_v2/modeling.py

See this annotation in the file changed.

@codecov codecov / codecov/patch

paddlenlp/transformers/deepseek_v2/modeling.py#L1162

Added line #L1162 was not covered by tests

Check warning on line 1182 in paddlenlp/transformers/deepseek_v2/modeling.py

See this annotation in the file changed.

@codecov codecov / codecov/patch

paddlenlp/transformers/deepseek_v2/modeling.py#L1182

Added line #L1182 was not covered by tests

Check warning on line 1201 in paddlenlp/transformers/deepseek_v2/modeling.py

See this annotation in the file changed.

@codecov codecov / codecov/patch

paddlenlp/transformers/deepseek_v2/modeling.py#L1195-L1201

Added lines #L1195 - L1201 were not covered by tests

Check warning on line 1273 in paddlenlp/transformers/deepseek_v2/modeling.py

See this annotation in the file changed.

@codecov codecov / codecov/patch

paddlenlp/transformers/deepseek_v2/modeling.py#L1266-L1273

Added lines #L1266 - L1273 were not covered by tests

Check warning on line 1276 in paddlenlp/transformers/deepseek_v2/modeling.py

See this annotation in the file changed.

@codecov codecov / codecov/patch

paddlenlp/transformers/deepseek_v2/modeling.py#L1276

Added line #L1276 was not covered by tests

Check warning on line 1278 in paddlenlp/transformers/deepseek_v2/modeling.py

See this annotation in the file changed.

@codecov codecov / codecov/patch

paddlenlp/transformers/deepseek_v2/modeling.py#L1278

Added line #L1278 was not covered by tests