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

qwen2_bugfix, add adamround vision UT #281

Merged
merged 3 commits into from
Oct 16, 2024
Merged

qwen2_bugfix, add adamround vision UT #281

merged 3 commits into from
Oct 16, 2024

Conversation

WeiweiZhang1
Copy link
Collaborator

No description provided.

@@ -721,7 +720,7 @@ def forward(m, hidden_states, *positional_args, **kwargs):
else:
self.inputs[name][key] = list(torch.split(alibi.to("cpu"), 1, dim=0))
elif "position_ids" in key or 'cache_position' in key:
if self.train_bs == 1 and self.not_share_rotary_pos_emb_flag:
if self.train_bs == 1 and self.not_share_position_ids_flag:
Copy link
Contributor

Choose a reason for hiding this comment

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

we could refine this later, we could add a shareable, contatable, etc for each key. In the future, we'd better not change the code in autoround.py but change the code in special_model_handle

Signed-off-by: Zhang, Weiwei1 <[email protected]>
@XuehaoSun XuehaoSun merged commit 7cfff96 into main Oct 16, 2024
10 checks passed
@XuehaoSun XuehaoSun deleted the qwen2_bugfix branch October 16, 2024 12:52
XuehaoSun pushed a commit that referenced this pull request Oct 16, 2024
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.

3 participants