【Bug】Fix attn_mask_startend_row_indices shape mismatch #2564
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! |
cheng221
force-pushed
the
develop
branch
2 times, most recently
from
873bd7d to
b38e4b5
Compare
lugimzzz
reviewed
Sep 8, 2025
| assert labels is not None | ||
|
|
||
| return self.criterion(logits, labels, loss_mask, router_loss=router_loss, mtp_logits=mtp_logits) | ||
| loss, _ = self.criterion(logits, labels, loss_mask, router_loss=router_loss, mtp_logits=mtp_logits) |
| tar -xvf alpaca_demo.gz | ||
| ``` | ||
| ### 模型下载 | ||
| ```bash |
There was a problem hiding this comment.
不需要加下载文档，后面可以直接用from_pretrained方式下载了
| # 微调Qwen2-0.5B-Instruct 需要12G显存左右 | ||
| python -u run_finetune.py ./config/qwen/sft_argument_qwen2_0p5b.json | ||
|
|
||
| # 微调ERNIE-4.5-0.3B-PT |
There was a problem hiding this comment.
这里先不用加ernie 4.5。先保证这ERNIEKit中能够训练就行
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Before submitting
testsfolder. If there are codecov issues, please add tests cases first.PR types
PR changes
Description
Fix attn_mask_startend_row_indices shape mismatch