An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

A collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。

☁️ 🚀 📊 📈 Evaluating state of the art in AI

Official repository of Evolutionary Optimization of Model Merging Recipes

🙌 OpenHands: Code Less, Make More

Free sampling of files from the purported Equation Group hack.

CodeGen2 models for program synthesis

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including OpenAI Agents SDK, CrewAI, Langchain, Autogen, AG2, and CamelAI

Accessible large language models via k-bit quantization for PyTorch.

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

Llama from scratch, or How to implement a paper without crying

My collection of machine learning papers

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Source code for Twitter's Recommendation Algorithm

Datasets, tools, and benchmarks for representation learning of code.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

Language model evaluation for morality and causality

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

Massively parallel training of machine-learning based weather and climate models

A curated list of reinforcement learning with human feedback resources (continually updated)

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.

This code accompanies the the paper Slow Momentum with Fast Reversion: A Trading Strategy Using Deep Learning and Changepoint Detection (https://arxiv.org/pdf/2105.13727.pdf).

🚂💨 Deep Momentum Networks for Time Series Strategies

Machine Learning Engineering Open Book

Code and model for the paper "Improving Language Understanding by Generative Pre-Training"