hu-po's repositories
ashenvenus
Entry to the 2023 Scroll Prize
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
speech2speech
🦜Have a conversation with anyone from any youtube video.
chaptergen
Creates video chapters from a .SRT file
quantumforget
do quantum networks forget?
audiocraft
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
igigi
rpi robot w/ stereo cam, 3 link head
ImageBind
ImageBind One Embedding Space to Bind Them All
llama2.c
Inference Llama 2 in one file of pure C
rerun
Log images, point clouds, etc, and visualize them effortlessly. Built in Rust using egui
ros2_documentation
ROS 2 docs repository
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.