OFA-Sys/OFASys
OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models
This system helps researchers and machine learning practitioners quickly build and train AI models that understand and generate content across multiple formats like text, images, audio, video, and even structured data. You feed it various types of input data and define your desired task with simple instructions, and it produces an AI model capable of performing tasks like image captioning, text summarization, or text-to-image generation. It's designed for those who want to create advanced AI applications that process and generate different kinds of information.
151 stars. No commits in the last 6 months.
Use this if you need to develop AI models that can understand and generate content across many different data types, like text, images, and audio, without deep engineering effort for each new task.
Not ideal if you are a non-technical user looking for a ready-to-use application rather than a system for building AI models.
Stars
151
Forks
13
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 07, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/OFA-Sys/OFASys"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dorarad/gansformer
Generative Adversarial Transformers
j-min/VL-T5
PyTorch code for "Unifying Vision-and-Language Tasks via Text Generation" (ICML 2021)
invictus717/MetaTransformer
Meta-Transformer for Unified Multimodal Learning
rkansal47/MPGAN
The message passing GAN https://arxiv.org/abs/2106.11535 and generative adversarial particle...
Yachay-AI/byt5-geotagging
Confidence and Byt5 - based geotagging model predicting coordinates from text alone.