A high-throughput and memory-efficient inference and serving engine for LLMs

DALL·E Mini - Generate images from a text prompt

Implementation of RLHF (Reinforcement Learning with Human Feedback) and GAN (Generative Adversarial Network) on top of the T5 architecture.

Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)