LLaVA-NeXT
LLaVA-NeXT copied to clipboard
LLaVA-VL
Hello, Are the pretraining code and data for LLaVA-OneVision open source ? Specially for Stage 2 (instruction tuning). It will help people build on your work.
Thanks so much for your amazing work! I was wondering if you could share the code for the LoRA fine-tuning for llava-video. Thanks!
Solve some error in this README file. The updated version works.
In Readme, or scripts please update with a $PWD or .Readme instruction to (llava) root@** :/app/LLaVA-NeXT# grep -r ROOT_DIR . **./scripts/video/demo/video_demo.sh:ROOT_DIR="/mnt/bn/vl-research/workspace/yhzhang/LLaVA-NeXT"** ./scripts/video/demo/video_demo.sh:if [ ! -e $ROOT_DIR ]; then ./scripts/video/demo/video_demo.sh:cd $ROOT_DIR...
Hi, First, thank you for the excellent work on this project! I encountered an issue while fine-tuning the model with multiple modes. Specifically, I observed the following behavior: - When...
Is there a script for performing DPO on LLaVa-One-Vision 7B?
Dear all, I have fine-tuned a LLaVA-OneVision (0.5B and 7B) with LLM and vision components frozen. The checkpoint output directory contains these files: ``` runs checkpoint-1000 ... ... checkpoint-22000 trainer_state.json...
Hello! Thank you for your outstanding work. However, I am sorry that my English is poor and I could not understand whether this code warehouse can realize the task of...
When using LLaVA-Llama3 for batch inference with the generate function, the results are incorrect.
When I use the generate function with batched input, the results are inconsistent compared to when the batch size is 1. There will be many empty strings sometimes. ```python #...
