Stars
Democratizing Reinforcement Learning for LLMs
A System for (Optimized) Semantic Computation
A high-throughput and memory-efficient inference and serving engine for LLMs
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.
DSPy: The framework for programming—not prompting—language models
[ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)
Official repo for consistency models.