Skip to content

Issues: Q-Future/Q-Align

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

13 Open 24 Closed
13 Open 24 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

when try to use flash_attention_v2, not find _prepare_4d_causal_attention_mask_for_sdpa
#40 opened Nov 6, 2024 by dongdk
commercial use of q-align
#39 opened Oct 16, 2024 by yasamin93
When I try to use koniq-10 for training, I encounter the problem that the loss is always 0.
#37 opened Sep 27, 2024 by style09131111
1
About the number of input video frames
#36 opened Sep 25, 2024 by elvindp
1
Full Training from Start：CUDA out of memory.
#35 opened Sep 19, 2024 by YUANMU227
2
Is this metric still depends on fixed transformers version?
#34 opened Sep 7, 2024 by Luciennnnnnn
RuntimeError: Error(s) in loading state_dict for MPLUGOwl2LlamaForCausalLM: size mismatch for norm.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([4096]). You may consider adding ignore_mismatched_sizes=True in the model from_pretrained method.
#33 opened Sep 6, 2024 by style09131111
1
hello,how can we use the multi-GPU inference ?
#32 opened Aug 29, 2024 by learn01one
'MPLUGOwl2Config' object has no attribute 'mlp_bias'
#31 opened Aug 28, 2024 by mattiasospetti
2
How Do I Perform Offline Inference? After a Model Is Downloaded to the Local Computer, the Model Cannot Be Executed?
#30 opened Aug 22, 2024 by hjb25286
1
About map the scores to the ranks
#28 opened Jul 14, 2024 by w-qhai
Is it possible to reproduce this project on Florence-2 to reduce memory requirements and speed up inference?
#27 opened Jul 1, 2024 by shiertier
Questions about modeling_llama2
#24 opened May 4, 2024 by lbc12345
ProTip! Exclude everything labeled bug with -label:bug.