Stars
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Official inference repo for FLUX.1 models
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains
A Framework of Small-scale Large Multimodal Models
A large-scale, fine-grained, diverse preference dataset (and models).
JS tokenizer for LLaMA 3 and LLaMA 3.1
A professional list on Large (Language) Models and Foundation Models (LLM, LM, FM) for Time Series, Spatiotemporal, and Event Data.
[NeurIPS 2024] SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challen…
A benchmark for evaluating learning agents based on just language feedback
A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
A modular RL library to fine-tune language models to human preferences
Your Automatic Prompt Engineering Assistant for GenAI Applications
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
A programming framework for agentic AI 🤖
A collection of facial landmark datasets and Python code to make use of them.
A repository for research on medium sized language models.
Large Language Models for Supply Chain Optimization
This is an AI agent for Street Fighter II Champion Edition.
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…
Instruct-tune LLaMA on consumer hardware
High-Resolution Image Synthesis with Latent Diffusion Models
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
A playbook for systematically maximizing the performance of deep learning models.