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 83 Closed
56 Open 83 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

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
Template in Pre-Training vs. SFT
#162 opened Dec 16, 2024 by serwansj
ValueError: Cannot use chat template functions because tokenizer.chat_template is not set and no template argument was passed! For information about writing templates and setting the tokenizer.chat_template attribute, please see the documentation at https://huggingface.co/docs/transformers/main/en/chat_templating
#160 opened Dec 16, 2024 by HAOYON-666
2
Efficient-Large-Model/VILA1.5-13b weird outputs
#158 opened Dec 12, 2024 by jhjangjh
Issues with the effectiveness of W4A16 quantization using AWQ
#157 opened Dec 10, 2024 by RanchiZhao
LongVILA - Base LLM not declared in the Paper?
#152 opened Nov 25, 2024 by liyucheng09
3
Issue: The size of tensor a (2) must match the size of tensor b (8) at non-singleton dimension 0
#151 opened Nov 20, 2024 by apfsds3bm9
2
Repetitive Output in LongViLa-LLama3-1024Frames
#149 opened Nov 9, 2024 by hb-jw
1
How to change openai inference call to docker for video?
#148 opened Nov 8, 2024 by cholland-nv
Unable to run Gradio demo: VILA with TinyChat
#146 opened Nov 4, 2024 by mitraavi
1
What is the conv_mode for VILA1.5-40b in video inference?
#145 opened Nov 3, 2024 by stdKonjac
2
How to get the stage 2 checkpoint path for 3_sft.sh
#143 opened Oct 18, 2024 by Qnancy
5
Long context video module only
#142 opened Oct 2, 2024 by MH-Python
Context size and examples for LongVILA
#141 opened Sep 30, 2024 by yulinzou
1
KeyError: 'llava_llama'
#138 opened Sep 9, 2024 by RajaAIStarter
1
Trying to run VILA on triton with triton_llm backend
#133 opened Sep 3, 2024 by dand-milestone
Dataset and Training code for Longvila
#132 opened Sep 2, 2024 by JcWang20
3
How to run longvila large context, sequence parallel inference?
#130 opened Aug 27, 2024 by zadeismael
20
How to run vila with TinyChatEngine with multiple understanding enabled?
#129 opened Aug 27, 2024 by yg1988
Can VILA do grounding jobs?
#128 opened Aug 26, 2024 by PredyDaddy
1
Plz fix run_vila.py line 65 output variable(s)
#127 opened Aug 25, 2024 by ziyaosg
TypeError: LlamaRotaryEmbedding.forward() got an unexpected keyword argument 'seq_len' when running VILA model inference
#126 opened Aug 25, 2024 by LanceLeonhart
6
how to run VILA1.5-40B-AWQ
#125 opened Aug 23, 2024 by chenxinhua
1
Expected Release Date for VILA^2 Model and Code
#124 opened Aug 23, 2024 by SZUHvern
1
Fine tuning and --evaluation_strategy argument
#122 opened Aug 22, 2024 by lyluh
1
ProTip! Exclude everything labeled bug with -label:bug.