LLaVA

Like 👍. Comment 💬. Subscribe 🟥. 🏘 Discord: https://discord.gg/pPAFwndTJd

YouTube: https://youtube.com/live/BJ98vicRYHg

X: https://twitter.com/i/broadcasts/1mnxepLdBlLJX

Twitch: https://www.twitch.tv/hu_po

References

https://github.com/haotian-liu/LLaVA

https://huggingface.co/liuhaotian/llava-v1.5-13b

https://arxiv.org/pdf/2310.03744.pdf

https://arxiv.org/pdf/2304.08485.pdf

Test images https://github.com/hu-po/LLaVA/tree/main/images

MINIGPT-5: INTERLEAVED VISION-AND-LANGUAGE GENERATION VIA GENERATIVE VOKENS https://arxiv.org/pdf/2310.02239.pdf

Ferret https://github.com/apple/ml-ferret/blob/main/figs/ferret_fig_diagram_v2.png

ScienceQA Benchmark https://paperswithcode.com/dataset/scienceqa

CC12M (Conceptual 12M) https://paperswithcode.com/dataset/cc12m

CLIP https://openai.com/research/clip https://huggingface.co/openai/clip-vit-large-patch14