Stars
AIRS-Bench: an AI Research Science benchmark for quantifying the end-to-end AI research abilities of LLM agents
Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!
An open-source, next-generation "runc" that empowers rootless containers to run workloads such as Systemd, Docker, Kubernetes, just like VMs.
Minimal reproduction of DeepSeek R1-Zero
All Algorithms implemented in Python
Efficient baselines for autocurricula in JAX.
Robust recipes to align language models with human and AI preferences
A (somewhat) minimal library for finetuning language models with PPO on human feedback.
Library and commandline tool for managing datasets on darwin.v7labs.com
Continuous Integration for LLM powered applications
Benchmarking RL generalization in an interpretable way.
Poetry plugin that allows for the creation of virtual environments using Poetry, without interfering with the Conda environment in which Poetry is installed
Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)
A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
API for the GPT-J language model 🦜. Including a FastAPI backend and a streamlit frontend
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
This repository contains demos I made with the Transformers library by HuggingFace.
Document Layout Analysis resources repos for development with PdfPig.