[AutoParallel] Refactor llama3.1 model in intermediate api #3116
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks for your contribution! |
|
|
sevenan2
force-pushed
the
refactor_model_2
branch
from
8d6ca3a to
88963b1
Compare
sevenan2
force-pushed
the
refactor_model_2
branch
3 times, most recently
from
7b15fd1 to
9524073
Compare
Contributor
Author
|
/re-run all-failed |
sevenan2
force-pushed
the
refactor_model_2
branch
from
9524073 to
05b7388
Compare
lugimzzz
reviewed
Dec 10, 2025
| query_states = self.q_proj(hidden_states).view(q_shape).transpose(1, 2) | ||
| key_states = self.k_proj(hidden_states).view(kv_shape).transpose(1, 2) | ||
| value_states = self.v_proj(hidden_states).view(kv_shape).transpose(1, 2) | ||
| query_states = self.q_proj(hidden_states).reshape(q_shape).transpose(1, 2) |
Contributor
Author
There was a problem hiding this comment.
为什么要改为reshape？
paddle transpose的问题，这里view之后虽然变成四维的，但是transpose还是认为该tensor是三维，即view之前的维度
| "down_proj", | ||
| ] | ||
|
|
||
| @classmethod |
Contributor
Author
There was a problem hiding this comment.
这个name_mapping的作用？
这个确实没什么用，现在版本里一些其他的模型还留着 ，所以没有删除
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
rename run_single_model to use_single_model_implementation
remove redundant notes
based on #2859