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.

Sign up for GitHub

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

Jump to bottom

qwen2vl的cutoff_len不生效报错 #6425

Closed
1 task done
ningcm opened this issue Dec 23, 2024 · 1 comment
Closed
1 task done

qwen2vl的cutoff_len不生效报错 #6425

ningcm opened this issue Dec 23, 2024 · 1 comment
Labels
invalid This doesn't seem right

Comments

@ningcm
Copy link

ningcm commented Dec 23, 2024

Reminder

  • I have read the README and searched the existing issues.

System Info

template: qwen2_vl
cutoff_len: 4096
max_samples: 1000
overwrite_cache: true
preprocessing_num_workers: 16

Reproduction

position_ids[..., i, attention_mask[i] == 1] = llm_positions.to(position_ids.device)
RuntimeError: shape mismatch: value tensor of shape [3, 4255] cannot be broadcast to indexing result of shape [3, 4095]

Expected behavior

......

Others

No response
@github-actions github-actions bot added the pending This problem is yet to be addressed label Dec 23, 2024
@ningcm ningcm closed this as completed Dec 23, 2024
@hiyouga hiyouga added invalid This doesn't seem right and removed pending This problem is yet to be addressed labels Dec 23, 2024
@yanglebupt
Copy link

How do you solve this problem, I have this too?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
invalid This doesn't seem right
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@hiyouga @ningcm @yanglebupt