Fangkai Jiao's repositories
llama-pipeline-parallel
A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free to copy code and launch discussions about the problems you have encoured.
MG-PFCM_outfit_rec
Personalized Fashion Compatibility Modeling via Metapath-guided Heterogeneous Graph Learning.
dpo-trajectory-reasoning
Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".
pytorch-transformers-template
This is a template for fast prototype relying on transformers, hydra, fairscale and deepspeed, etc.
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
nimo-markdown-cv
Maintain your CV in Markdown :sparkles:
OpenPSG
Benchmarking Panoptic Scene Graph Generation (PSG), ECCV'22
RAP
Reasoning with Language Model is Planning with World Model
reflexion
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
SparkJiao.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
ZoomNet
Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection, CVPR 2022