Skip to content

Issues: Vision-CAIR/LongVU

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

27 Open 17 Closed
27 Open 17 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

May I ask which parts were trained during the fine-tuning phase
#47 opened Mar 1, 2025 by SplendidYuan
Question about inference configuration and reproduction of results
#46 opened Feb 25, 2025 by liys0304
Any way to calculate the sum of input tokens
#45 opened Feb 23, 2025 by Hotpottttt
Is deepspeed possible for fine-tuning LongVU?
#44 opened Feb 3, 2025 by tcm03
Out of memory when using 8 * A800-80G for video inference
#43 opened Jan 27, 2025 by caichaoxiang
3
Checkpoint loading issue: ValueError
#41 opened Jan 24, 2025 by andyhandsom6
1
Re. evaluation script
#40 opened Jan 20, 2025 by pritamqu
Where to find the answers of egoschema?
#39 opened Jan 14, 2025 by jyC23333
1
Training Time
#38 opened Jan 13, 2025 by Hui-design
3
Request for requirements.txt for LLaMA-3.2 Image Training
#36 opened Jan 8, 2025 by tsw123tsw
Minor bug in MVBench style evaluation when the dataset size isn't divisible by the number of GPUs
#35 opened Dec 18, 2024 by geomlyd
1
Is the parameter "vision_sampler_0.pos_embed_i" learnable?
#34 opened Dec 14, 2024 by jiinhui
The weights after sft of video data cannot be inferred
#33 opened Dec 11, 2024 by orzgugu
3
The accuracy of llama2_2_3B on mvBench is a bit low.
#32 opened Dec 6, 2024 by DuZzzs
1
Fine-tuning from an pre-trained image checkpoint has mismatch issue
#31 opened Dec 5, 2024 by Amshaker
attention warning and incomplete text description
#28 opened Dec 1, 2024 by Holmes-GU
1
Selective Feature reduction via cross modal query
#25 opened Nov 30, 2024 by insafim
1
Question: Video vs Frames?
#24 opened Nov 26, 2024 by cbasavaraj
4
Need understanding number of tokens
#22 opened Nov 18, 2024 by miguelcarvtalka
4
Did you ever encounter issues with Trainer's _save_checkpoint and FSDP?
#21 opened Nov 15, 2024 by geomlyd
13
Are there any plans to release the fine-tuning code?
#20 opened Nov 13, 2024 by miguelcarvtalka
1
long videos inference error
#17 opened Nov 8, 2024 by cmhhw
16
Cannot find Selective Feature Reduction via Cross modal Query code
#16 opened Nov 7, 2024 by zzzz123-0708
1
Error for video SFT
#14 opened Nov 6, 2024 by yanlai00
5
AttributeError: 'NoneType' object has no attribute 'image_mean'
#10 opened Nov 5, 2024 by cutiyu
1
ProTip! What’s not been updated in a month: updated:<2025-02-09.