Skip to content

Conversation

@micelvrice
Copy link
Contributor

PR types

New features

PR changes

Models

Description

Paddle implementation of LongLoRA

Copy link
Contributor

@lugimzzz lugimzzz left a comment

Choose a reason for hiding this comment

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

lgtm

@lugimzzz lugimzzz merged commit cda5279 into PaddlePaddle:develop Mar 4, 2025
14 of 16 checks passed
@paddle-bot
Copy link

paddle-bot bot commented Mar 4, 2025

Thanks for your contribution!

"zero_padding": false,
"use_flash_attention": true,
"unified_checkpoint": true,
"pissa": false,
Copy link
Contributor

Choose a reason for hiding this comment

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

这里的配置有问题,没有打开use_ssa,也没开use_long_strategy需要写一个能跑的配置

@@ -0,0 +1,74 @@
finetune:
Copy link
Contributor

Choose a reason for hiding this comment

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

https://github.com/PaddlePaddle/PaddleNLP/blob/develop/tests/llm/test_lora.py 参考上线需要写一个tests/llm/test_longlora.py才能执行

import paddlenlp
from paddlenlp.transformers.llama.modeling import get_triangle_upper_mask

ssa_group_size_ratio = 1 / 4
Copy link
Contributor

Choose a reason for hiding this comment

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

ssa_group_size_ratio这里写死了如何通过model_args.ssa_group_size_ratio控制

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants