LLaVA-NeXT
LLaVA-NeXT copied to clipboard
Hi there! I clone the tensors here: git clone https://huggingface.co/lmms-lab/llava-next-interleave-7b And I do the setup as is in the readme (which needs an upgrade for gradio (pip install --upgrade gradio)...
+ Add assert to make sure number of images == number of image tokens in inputs + Fix the case [where num_images == 0](https://github.com/LLaVA-VL/LLaVA-NeXT/blob/inference/llava/model/llava_arch.py#L263): + We don't need to use...
When I was trying to run the gradio demo with the new llava-next-interleave-7b model, I ran into the following two errors. Any ideas?
Thanks for your great job. When will the training code open sourced?
I found something strange when loading the model. It seems that you have released the vision_tower during training, but when loading the vision_tower, you did not load the gradient-updating parameters,...
Will the interleaved data opensource?
I think the 0.5B model already shown strong performance in Multi-image Evaluation, will this model release later? Thanks.
hi, I am trying to run `llava/eval/model_video_chatgpt_general.py`, but I noticed that there is no `eval` folder within the `llava` directory. Is that wrong?
Hey all! The video models are all supported in Transformers now and will be part of the v4.42 release. Feel free to check out the model checkpoints [here](https://huggingface.co/collections/llava-hf/llava-next-video-6666a9173a64c7052930f153). To get...
Is this going to be on the transformers library? Seems like it's going to be big.