LLaVA-NeXT

LLaVA-NeXT copied to clipboard

Eval results

6

Hi, I evaluated your 7B model, but the results in new introduced benchmarks are not normal.

liguopeng0923

Different Reported Results on NeXT-QA and Egoschema

3

Hi Team, I saw that LLaVA-NeXT-Video-32B-Qwen obtains 77.31%, 63% accuracy on NeXT-QA and Egoschema here: https://huggingface.co/lmms-lab/LLaVA-NeXT-Video-32B-Qwen. On the other hand, LLaVA-NeXT-Video-DPO (34B) achieves 27.30% accuracy on NeXT-QA dataset. Why the...

jongwoopark7978

output of the demo code

1

I tried to run the [demo code from here](https://github.com/LLaVA-VL/LLaVA-NeXT/blob/inference/docs/LLaVA-NeXT.md). The output is ``` ['!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!'] ``` Do someone have the same issue and how do you solve it? Thanks!

zshyang

Do we have some inference accelerate method for new llava-next-video models?

1

Hi, Amazing job for new llava-next-video model! Since it has 34B params and maybe need more than 1 GPU, so do we have support some inference accelerate method for new...

LetheRiver0

Thank you llava-next team for releasing the powerful models and having them ready on huggingface (shout out to HF team as well). I've put up a code base https://github.com/zjysteven/lmms-finetune which...

zjysteven

LLaVA-NeXT-Interleave Training Details

3

Hello. Thanks for your excellent work! Earlier, I reproduced LLaVA-NeXT-Image training and got the desired performance, and I am now trying to reproduce LLaVA-NeXT-Interleave training. I would like to inquire...

friedrichor

how to get results?

1

My gradio version is 4.38.1. But the operation keeps waiting in the queue, and there is no log display in the background program, as shown below. What's going on? 

luyao-cv

Hi, Why is this functionality not implemented? https://github.com/LLaVA-VL/LLaVA-NeXT/blob/1654303050a429f5c0dbb97033bf24a2263531cf/llava/model/llava_arch.py#L233-L235 What is needed to implement this? Best, Orr

orrzohar

Can we add preprocessor_config.json for llava-next-interleave-qwen-7b model on Huggingface?

1

Hi, I am using sglang to deploy llava-next-interleave-qwen-7b, but i found there is no preprocessor_config.json for llava-next-interleave-qwen-7b model, could we add this to huggingface? Or do we have some other...

LetheRiver0

I would like to ask the author and those who are involved in the work of LLAVA NEXT. I would like to provide Chinese OCR capability for llava next, attempting...

Bill-WangJiLong