Stars
A native PyTorch Library for large model training
Retrieve data from Binance and simulate high-frequency trading on them using the GARCH model
Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas…
A novel approach for synthesizing tabular data using pretrained large language models
Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.
LangChain-based RAG system for querying US & EU AI regulations and Stanford Encyclopedia of Philosophy articles pertinent to AI ethics etc.
A curated list of awesome open-source libraries for production LLM
[CVPR 2024] VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis
Video Swin Transformer - PyTorch
(CVPR2024)RMT: Retentive Networks Meet Vision Transformer
Tutorials that cover topics from basics to advanced fMRI analysis
Predicting Alzheimer’s disease progression trajectory and clinical subtypes using machine learning
Code for analysis of ADNI data
Python package to access a cacophony of neuro-imaging file formats
DIPY is the paragon 3D/4D+ imaging library in Python. Contains generic methods for spatial normalization, signal processing, machine learning, statistical analysis and visualization of medical imag…
Agentic components of the Llama Stack APIs
Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch
TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.
Utilities intended for use with Llama models.
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882
This repository contains demos I made with the Transformers library by HuggingFace.
A modular graph-based Retrieval-Augmented Generation (RAG) system