open-mmlab/Multimodal-GPT
Multimodal-GPT
This project helps you create intelligent chatbots that can understand both text and images, allowing for richer, more natural conversations. You input various visual and language instruction datasets, and the output is a finely tuned chatbot capable of responding to complex queries that involve visual information. This is ideal for researchers or developers looking to build advanced AI assistants for diverse applications.
1,517 stars. No commits in the last 6 months.
Use this if you want to develop a conversational AI that can interpret and respond to queries involving both visual content and text instructions.
Not ideal if you are looking for a pre-built, ready-to-deploy multimodal chatbot without any fine-tuning or development work.
Stars
1,517
Forks
130
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/open-mmlab/Multimodal-GPT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TinyLLaVA/TinyLLaVA_Factory
A Framework of Small-scale Large Multimodal Models
zjunlp/EasyInstruct
[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.
rese1f/MovieChat
[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
haotian-liu/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
NVlabs/Eagle
Eagle: Frontier Vision-Language Models with Data-Centric Strategies