LLaVA-NeXT
LLaVA-NeXT copied to clipboard
LLaVA-VL
First of all, thank you for open-sourcing this great work! I notice that in the demo code released, though the `image_aspect_ratio` was set to `anyres`, the images are processed as...
Can you provide a batch video inference interface for llava-next-interleave? I have currently implemented a video batch-inference interface for llava-next-interleave, but when I set the batch size to 2, it...
When importing (even selective) from conversation.py, the AutoTokenizer.from_pretrained("meta-llama....") gets triggered and tries to access huggingface, and for me personally I have no access to this model which causes an error....
I am encountering an error when attempting to reuse the past_key_values for generating text based on image-text pairs. ``` pretrained = "lmms-lab/llama3-llava-next-8b" model_name = "llava_llama3" tokenizer, model, image_processor, max_length =...
I cloned the "**lmms-lab/LLaVA-NeXT-Interleave-Bench**" dataset from Huggingface. I checked several evaluation samples in it and noticed (possible) mismatch between certain QA-pairs and their associated images. For example: **in "multi_image_in_domain.json", the...
when i run bash , error occurs > bash scripts/video/demo/video_demo.sh /data/checkpoints/llama3-llava-next-8b vicuna_v1 32 2 average after no_token True /mnt/data/user/tc_agi/qmli/LLaVA-NeXT-inference/LLaVA-NeXT-inference/playground/demo/xU25MMA2N4aVtYay.mp4 Traceback (most recent call last): File "/mnt/data/user/tc_agi/qmli/LLaVA-NeXT-inference/LLaVA-NeXT-inference/playground/demo/video_demo.py", line 316, in run_inference(args)...
as the title tells. Are there any specific plan for releasing the training code?
Trying to deploy and run demo on a 4 A6000 cluster but it seemed that the runtime froze without any exceptions... Could there be any possible problems? Sorry for asking...
Hello! I used the following demo code but got a weird inference output: ['�������� |> |> |> |> |> |> |> |> |> |> |> |> |> |> |> |>...
