Accessible large language models via k-bit quantization for PyTorch.
- llm
- machine-learning
- pytorch
- qlora
142,273 visible repositories in the index
553–576 of 8,991 · Most stars
Accessible large language models via k-bit quantization for PyTorch.
Out-of-Core hybrid Apache Arrow/NumPy DataFrame for Python, ML, visualization and exploration of big tabular data at a billion rows per second 🚀
⚡ TabPFN: Foundation Model for Tabular Data ⚡
A resource for learning about Machine learning & Deep Learning
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
Ready-to-run Docker images containing Jupyter applications
FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
Bandit is a tool designed to find common security issues in Python code.
Text-audio foundation model from Boson AI
A configurable set of panels that display various debug information about the current request/response.
Uniform Manifold Approximation and Projection
Lighter web automation with Python
BoxMOT: Pluggable multi-object tracking in Python and C++ for axis-aligned and oriented boxes, now with Helm deployment for continuous camera tracking on Kubernetes.
Depth-Aware Video Frame Interpolation (CVPR 2019)
Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy
Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version
TranslatedINFO-SPIDER is a crawler toolbox 🧰 that brings many data sources together in one place, designed to help users get their own data back safely and quickly. The tool's code is open source and the process is transparent. Supported data sources include GitHub, QQ Mail, NetEase Mail, Alibaba Mail, Sina Mail, Hotmail, Outlook Mail, JD.com, Taobao, Alipay, China Mobile, China Unicom, China Telecom, Zhihu, Bilibili, NetEase Cloud Music, QQ friends, QQ groups, generating a Moments (WeChat friend circle) photo album, browser browsing history, 12306, cnblogs (博客园), CSDN blog, OSChina blog, Jianshu.
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation