LLM training in simple, raw C/CUDA

Winning solution for the Kaggle Feedback Prize Challenge.

Inference Llama 2 in one file of pure C

A simple wrapper to call openAI's chatGPT on the terminal written in Python

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

wandbot is a technical support bot for Weights & Biases' AI developer tools that can run in Discord, Slack, ChatGPT and Zendesk

🦜🔗 Build context-aware reasoning applications

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

31st place silver medal solution to USPPPM Kaggle competition

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

Neural Networks: Zero to Hero

ML Collections is a library of Python Collections designed for ML use cases.

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

🎖️ 4th place solution in the Feedback Prize Competition🎖️

An unsupervised feature selection technique using supervised algorithms such as XGBoost

a generalist algorithm for cellular segmentation with human-in-the-loop capabilities

Hydra is a framework for elegantly configuring complex applications

Deep Learning for humans

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

OpenMMLab Detection Toolbox and Benchmark

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

This repository contains code I wrote for all the competitions that I participated in

Tez is a super-simple and lightweight Trainer for PyTorch. It also comes with many utils that you can use to tackle over 90% of deep learning projects in PyTorch.

Learn how to design, develop, deploy and iterate on production-grade ML applications.

🥈50th place in Bristol-Myers Squibb – Molecular Translation competition🥈