Robust recipes to align language models with human and AI preferences

🌀 𝗧𝗵𝗲 𝗙𝘂𝗹𝗹 𝗦𝘁𝗮𝗰𝗸 𝟳-𝗦𝘁𝗲𝗽𝘀 𝗠𝗟𝗢𝗽𝘀 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸 | 𝗟𝗲𝗮𝗿𝗻 𝗠𝗟𝗘 & 𝗠𝗟𝗢𝗽𝘀 for free by designing, building and deploying an end-to-end ML batch system ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 2.5 𝘩𝘰𝘶𝘳𝘴 𝘰𝘧 𝘳𝘦𝘢𝘥𝘪𝘯𝘨 & 𝘷𝘪𝘥𝘦𝘰 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭𝘴

The easiest way to serve AI apps and models - Build reliable Inference APIs, LLM apps, Multi-model chains, RAG service, and much more!

Use Large Language Models in Your React App

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Official Code for DragGAN (SIGGRAPH 2023)

Train transformer language models with reinforcement learning.

Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.

🦜🔗 Build context-aware reasoning applications

Free MLOps course from DataTalks.Club

All Algorithms implemented in Python

Labs and demos for courses for GCP Training (http://cloud.google.com/training).

Official Repository for Code associated with 'Practical Natural Language Processing' book by O'Reilly Media

Jupyter notebooks for the Natural Language Processing with Transformers book

Cross-platform, customizable ML solutions for live and streaming media.

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

This repository consists of the code samples, assignments, and notes for the Java data structures & algorithms + interview preparation bootcamp of WeMakeDevs.

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

Tensors and Dynamic neural networks in Python with strong GPU acceleration

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

An open-source AutoML Library based on PyTorch

Python package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation

A deep learning library for video understanding research.

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

A collection of loss functions for medical image segmentation

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125