Skip to content
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

[Model] Add Qwen2 model. #330

Merged
merged 1 commit into from
Apr 23, 2024
Merged

[Model] Add Qwen2 model. #330

merged 1 commit into from
Apr 23, 2024

Conversation

marvin-Yu
Copy link
Contributor

No description provided.

@changqi1
Copy link
Contributor

What is the differences between Qwen1.0 vs Qwen 2.0?

RmsNorm finalLN;
};

REGISTER_DECODER(Qwen2LLM, qwen2, float)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What's the error when put such macro to cpp file?

Copy link
Contributor

@Duyi-Wang Duyi-Wang Apr 22, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What's the error when put such macro to cpp file?

Putting in a CPP file won't trigger the execution of this macro, it confused me. It instantiates a static object of a registrar.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

not the scope of this PR.

"initializer_range": 0.02,
"intermediate_size": 2816,
"max_position_embeddings": 32768,
"max_window_layers": 21,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

what is the meaning for max_window_layers?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done

Copy link
Contributor

@Duyi-Wang Duyi-Wang left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

copy right's year

benchmark/run.sh Outdated
@@ -1,5 +1,5 @@
#!/bin/bash
# set -x
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

unset

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

unnecessary

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Unnecessary

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Unnecessary

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Unnecessary

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done

@changqi1
Copy link
Contributor

What is the differences between Qwen1.0 vs Qwen 2.0?

If Qwen2.0 have no difference w/ LLama2. Do we need to inherit from LLama2?

@pujiang2018 pujiang2018 merged commit d37178d into main Apr 23, 2024
1 check passed
@marvin-Yu marvin-Yu mentioned this pull request Apr 23, 2024
@Duyi-Wang Duyi-Wang deleted the model/add_qwen2 branch April 23, 2024 06:59
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants