- Kampala, Uganda
- smugisha.com
- @smugisha_
Highlights
Lists (2)
Sort Name ascending (A-Z)
Stars
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.
String-to-String Algorithms for Natural Language Processing
a light-weight Markdown editor based on React. 一款轻量的基于React的markdown编辑器
Web interface for browsing, search and filtering recent arxiv submissions
A collection of design patterns/idioms in Python
Generate 3D objects conditioned on text or images
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
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.
An extremely fast Python linter and code formatter, written in Rust.
State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.
Unofficial PyTorch Implementation of UnivNet Vocoder (https://arxiv.org/abs/2106.07889)
OpenAI CLIP text encoders for multiple languages!
A multi-voice TTS system trained with an emphasis on quality
Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Using Low-rank adaptation to quickly fine-tune diffusion models.
Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, Du…
High-Resolution Image Synthesis with Latent Diffusion Models
Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch
[ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)
🦜🔗 Build context-aware reasoning applications
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.