llava-rlhf.github.io - LLaVA-RLHF

Description: Visual Instruction Tuning

Example domain paragraphs

Code Demo Dataset (RM) Dataset (SFT) MMHal-Bench Model (13b) Model (7b) LLaVA-RLHF represents the first open-source RLHF-trained large multimodal model for general-purpose visual and language understanding, achieving impressive visual reasoning and perception capabilities mimicking spirits of the multimodal GPT-4 and setting a new state-of-the-art accuracy on LLaVA-Bench, MMBench, and MMHal-Bench. We propose a new alignment algorithm called Factually Augmented RLHF (Fact-RLHF) that augments the reward model

Image Drop Image Here - or - Click to Upload Preprocess for non-square image Crop Resize Pad Examples What is unusual about this image? What are the things I should be cautious about when I visit here? Parameters ▼ LLaVA Chatbot Textbox Submit 👍 Upvote 👎 Downvote ⚠️ Flag 🔄 Regenerate 🗑️ Clear history Terms of use By using this service, users are required to agree to the following terms: The service is a research preview intended for non-commercial use only. It only provides limited safety measures and may g

The service is a research preview intended for non-commercial use only, subject to the model License of LLaMA, Terms of Use of the data generated by OpenAI, and Privacy Practices of ShareGPT. Please contact us if you find any potential violation.

Links to llava-rlhf.github.io (3)

tobiaslee.top Stay Hungry,Stay Foolish.
vlf-silkie.github.io Silkie
mm-arxiv.github.io Multimodal ArXiv