Fengyuan Hu's repositories
sparse_autoencoder
Sparse Autoencoder for Mechanistic Interpretability
AI-Vtuber
本地部署chatglm生成并以语音回复你的bilibili直播弹幕 Use chatglm to generate and reply your bilibili live danmu with voice
ChatPaper
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文总结+润色+审稿+审稿回复
dreamerv3
Mastering Diverse Domains through World Models
fish-diffusion
An easy to understand TTS / SVS / SVC framework
GEMS-GCN
DGL implementation of GCN for link prediction, trained on ogbl-colab dataset.
HuFY-dev.github.io
My personal academic website
nnsight
The nnsight package enables interpreting and manipulating the internals of deep learned models.
SAELens
Training Sparse Autoencoders on Language Models
SimplerEnv
Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge)
so-vits-svc
SoftVC VITS Singing Voice Conversion
so-vits-svc-gui
so-vits-svc fork with REALTIME support (voice changer) and greatly improved interface.
toy_gpt
This is a toy example of GPT
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities