LLM
Large Language Model Text Generation Inference
Secrets of RLHF in Large Language Models Part I: PPO
Neo4j graph construction from unstructured data using LLMs
Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"
Code for "Learning to summarize from human feedback"
Code for the paper Fine-Tuning Language Models from Human Preferences
The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
An open-source RAG-based tool for chatting with your documents.
Code for the paper "Training Diffusion Models with Reinforcement Learning"
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
A blazing fast inference solution for text embeddings models
Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization
A high-throughput and memory-efficient inference and serving engine for LLMs
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
🚀 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
Make huge neural nets fit in memory
Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Mix of Minimal Optimal Sets (MMOS) of dataset has two advantages for two aspects, higher performance and lower construction costs on math reasoning.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models
Streamlit LLM app examples for getting started
Streamlit — A faster way to build and share data apps.
Utilities intended for use with Llama models.
Agentic components of the Llama Stack APIs
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step