git
ask
hub
Privacy
Terms
Sign in with GitHub
llava-vl/llava-next
↗
Stars ·
4,699
Language ·
Python
License ·
Apache-2.0
Simplify and Visualize This Repo
Scan the safety of this repo
Self Host this repo
Check out more work of Developer: llava-vl
Ask anything about this repo to start.
I have the LLaVA-NeXT repo. How do I load a LLaVA-OneVision checkpoint from Hugging Face and run inference on a single image using Python?
Using LLaVA-NeXT, write a Python script that takes a video file as input and asks the model to summarize what happens in the video.
I want to fine-tune a LLaVA-NeXT model on my own image-question-answer dataset. Walk me through the training script arguments I need to set in this repo.
How do I use LLaVA-Critic-R1 from the llava-next repo to evaluate and score a response generated by another AI model?
Show me how to run LLaVA-NeXT-Interleave on a document that contains both images and text mixed together, using the code in this repository.
Full explanation on explaingit →
📎
Send
By chatting or signing in you agree to the
Terms
and chat-message logging (revocable in
History
).