~ / leaderboard / skill / llava
Skill · #3516

llava

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, vi

5rigs use it
0%of all rigs
7.7kavg rig context tax

Get it

$ npx degit KalarisLabs/research-agent-skills/skills/llava .claude/skills/llava

From the most-starred rig that ships it: KalarisLabs/research-agent-skills. Same-named skills in different rigs may differ — review before use.

Often used together with

Rigs using llava (5)

copied ✓