Titan AI LogoTitan AI

LLaVA

22,916
2,532
Python

项目描述

LLaVA is a large language and vision model that integrates visual instruction tuning to achieve capabilities beyond GPT-4, focusing on multimodality and visual-language learning.

Project Information

Created on 4/17/2023
Updated on 7/2/2025

Categories

ai-content-generation
conversational-assistant
image-processing

Tags

open-source-community
multimodal
model-deployment
data-processing
research-frontier

Topics

foundation-models
visual-language-learning
instruction-tuning
llava
llama-2
multimodal
chatgpt
llama
llama2
multi-modality
vision-language-model
gpt-4
chatbot