https://github.com/cliangyu/teebeecee
A repo of pattern recognition data analytics by Team TeeBeeCee.
https://github.com/cliangyu/llava
Visual Instruction Tuning: Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.
https://github.com/cliangyu/open_flamingo
An open-source framework for training large multimodal models.
https://github.com/cliangyu/megatron-deepspeed
Ongoing research training transformer language models at scale, including: BERT & GPT-2
https://github.com/cliangyu/llmspeculativesampling
Fast inference from large lauguage models via speculative decoding
https://github.com/cliangyu/slowfast
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
https://github.com/cliangyu/qlib
Qlib is an AI-oriented quantitative investment platform, which aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment. With Qlib, you can easily try your ideas to create better Quant investment strategies. An increasing number of SOTA Quant research works/papers are released in Qlib.
https://github.com/cliangyu/openpsg
Benchmarking Panoptic Scene Graph Generation (PSG), ECCV'22
https://github.com/cliangyu/ofa
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
https://github.com/cliangyu/mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark