VITA-MLLM VITA issues - Githubissues

VITA-MLLM / VITA

✨✨VITA: Towards Open-Source Interactive Omni Multimodal LLM

Other

969 stars 59 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

memory required for fine-tuning

#58 Pengjie-W opened 2 days ago
0
Is the data for state classification avaiable?

#57 fanghgit opened 2 weeks ago
0
RuntimeError: The size of tensor a (56640) must match the size of tensor b (80) at non-singleton dimension 2

#56 sankexin closed 2 weeks ago
1
Bad performances on English question in interactive demo.

#55 LiuMY13 opened 4 weeks ago
0
Does it support passing in multiple audio files and text prompts?

#54 binzhouu opened 4 weeks ago
0
显卡需求

#53 xiaodongyichuan opened 4 weeks ago
5
Can not join the WeChat group.

#52 LiuMY13 opened 1 month ago
0
when train KeyError: None

#51 sankexin opened 1 month ago
2
audio_processor error：cannot open q1.wav!!!!!!!!!!!!!!!!

#50 sankexin closed 2 weeks ago
5
InternViT-300M-448px下载之后应该放在哪里

#49 LIE624 opened 1 month ago
1
微信群二维码已过期

#48 haojun0001 closed 1 month ago
2
Does support audio multi-turn chat?

#47 MonolithFoundation closed 1 month ago
1
请问下是否支持输入是语音，输出是语音的形式？

#46 learn01one closed 2 months ago
2
Assertion Failed during training

#45 zealot52099 opened 2 months ago
2
微信二维码过期了。

#44 stevezhang88 closed 2 months ago
1
Fail to run video_audio_demo.py with ValueError

#43 superobk closed 1 month ago
3
The number of required GPUs exceeds the total number of available GPUs in the placement group.

#42 JosenJin opened 2 months ago
3
"RuntimeError: CUDA error: an illegal memory access was encountered" when running web_ability_demo

#41 superobk closed 2 months ago
3
关于状态<2>的问题

#40 liyunlongaaa closed 2 months ago
3
无法访问摄像头和麦克风

#39 zhongJY1998 closed 2 months ago
3
微信二维码已过期，麻烦更新一下

#38 Mahaotian1 closed 2 months ago
2
how many languages supported?

#37 XingWang1234 closed 2 months ago
2
测试了 vita，为何 vita 看不到周围的环境（摄像头已打开）

#36 future911 closed 2 months ago
0
run web_interactive_demo ,input audio err

#35 aigyp closed 2 months ago
1
无法连接摄像头，并且页面提示找不到麦克风

#34 future911 closed 2 months ago
4
out of memory when running demo via "python -m web_demo.web_ability_demo demo_VITA_ckpt/

#33 future911 closed 2 months ago
2
Update README.md

#32 Kidand opened 2 months ago
0
Update README.md

#31 Kidand closed 2 months ago
0
Significant poor performance observed

#30 binisalegend closed 2 months ago
5
What prompts are used for the audio capacity evaluation?

#29 Danield21 closed 2 months ago
4
Web DEMO: ValueError: Unrecognized configuration class to build an AutoTokenizer.

#28 Kidand closed 2 months ago
7
ValueError: Trying to set a tensor of shape torch.Size([4096, 4096]) in "weight" (which has shape torch.Size([4096, 20480])), this looks incorrect.

#27 mccs-2024 closed 2 months ago
1
VideoMME Evaluation Setting

#26 QAQdev closed 2 months ago
2
Data Concatenation: how to avoid sample contamination during training

#25 xiabingquan closed 2 months ago
5
Inconsistent results of VideoMME between github repo and tech report

#24 QAQdev closed 2 months ago
3
Error while running python -m web_demo.web_ability_demo demo_VITA_ckpt/

#23 sambalshikhar closed 2 months ago
5
ValueError: limit_mm_per_prompt is only supported for multimodal models.

#22 MeinhardZhou closed 2 months ago
3
torch out of memory when running demo via "python -m web_demo.web_ability_demo demo_VITA_ckpt/"

#21 superobk closed 2 months ago
6
I meet AttributeError: __pydantic_core_schema__ when i run web_interactive_demo.py

#20 hb-jw closed 2 months ago
2
flash-attn building failed, may I have some solution to resolve it?

#19 superobk closed 2 months ago
1
How to finetune?

#18 kike-0304 closed 2 months ago
3
问一下哈，代码还开源么

#17 stanpcf closed 2 months ago
6
Discrepancy in the Number of Tokens Output by InternViT-300M-448px

#16 rotem154154 closed 3 months ago
1
Open-Source Timeline Inquiry

#15 hb-jw closed 3 months ago
1
Request for training code, deployment code, and model weights.

#14 luojy95 closed 3 months ago
1
你好，这个模型可以选择不同的输入形态，输出形态

#13 seeyourcell closed 3 months ago
1
有开源部分数据的计划吗？

#12 liwenju0 closed 3 months ago
1
模型文件在哪

#11 dandanW91 closed 3 months ago
1
download url

#10 cscpswang closed 3 months ago
1
multimodal

#9 xubin983010 closed 3 months ago
1