Skip to content

Issues: NVlabs/VILA

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

56 Open 120 Closed
56 Open 120 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

Questions about the json mode.
#212 opened Mar 7, 2025 by Zhoues
1
About dataset config to preform the Training (Stage-one Alignment).
#211 opened Mar 5, 2025 by Columbine21
1
Fail to run server.py script using VILA series
#210 opened Mar 5, 2025 by JENNSHIUAN
1
minimal example to modify inference configuration
#209 opened Mar 3, 2025 by pritamqu
Clarication on training dataset sizes or if subsamples used.
#207 opened Feb 28, 2025 by neelsj
3
Is there any DataCollatorForSupervisedDatasetSeqParallel for video dataset?
#205 opened Feb 26, 2025 by ymbao97
1
Multi-modal Packing and Overflow of Max Sequence Lengths
#204 opened Feb 24, 2025 by ziqipang
[openai-api error] Failed to response: Error code: 500 - {'error': 'Invalid style: SeparatorStyle.AUTO'}
#201 opened Feb 18, 2025 by olivetom
1
[Running VILA API server] Errors during API Server implementation
#198 opened Feb 13, 2025 by jseo7
3
what is the difference between "NVILA-Lite", "NVILA" and "NVILA-video"?
#196 opened Jan 26, 2025 by MengHao666
10
Evaluating needle in a haystack the responses are abnormal
#194 opened Jan 19, 2025 by hshc123
1
Is there any news about the serving scripts updates?
#193 opened Jan 18, 2025 by lmh87883819
2
Error when running NVILA-8B-Video
#190 opened Jan 16, 2025 by yuanyehome
1
NVILA FP8 training
#189 opened Jan 15, 2025 by xpx9826
1
The dataset problem of "Step-3: Supervised fine-tuning"
#188 opened Jan 14, 2025 by BaiLing09
1
How to train a video inference model using this framework?
#186 opened Jan 13, 2025 by HAOYON-666
1
Confusion about answer_embeds Usage in eval_forward for Inference
#185 opened Jan 12, 2025 by hshc123
openai.InternalServerError: Error code: 500 - {'error': "'NoneType' object is not iterable"}
#182 opened Jan 10, 2025 by HAOYON-666
3
docker NVILA inference error
#176 opened Jan 2, 2025 by JIA-HONG-CHU
@Lyken17
3
How to quantize NVILA with awq？
#174 opened Dec 30, 2024 by Kibry-spin
2
NVILA Fine Tuning Process Not clear
#172 opened Dec 27, 2024 by rahuljoshi078
1
NVILA-15B Fine Tuning
#171 opened Dec 27, 2024 by rahuljoshi078
1
Use vila-infer to reason among multiple images
#168 opened Dec 20, 2024 by Hetznero
1
I can correctly obtain reasoning results using this code：“vila-infer \ --model-path /data/workspace/zhaoyong/model/weight_files/VILA1.5-3B \ --conv-mode vicuna_v1 \ --text "Please describe the video." \ --media /data/workspace/zhaoyong/data/安全帽.mp4”, but I get an error when using this code：“python -W ignore server.py \ --port 8000 \ --model_path /data/workspace/zhaoyong/model/weight_files/VILA1.5-3B \ --conv_mode vicuna_v1”. Why is that? How should I solve it?
#163 opened Dec 18, 2024 by HAOYON-666
1
Template in Pre-Training vs. SFT
#162 opened Dec 16, 2024 by serwansj
3
ProTip! Follow long discussions with comments:>50.