structured outputs for llms

Serve, optimize and scale PyTorch models in production

An application that integrates AWS CloudWatch logs and Slack

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Lambda function that sends messages to a Slack webhook

Lime: Explaining the predictions of any machine learning classifier

Must-read papers on prompt-based tuning for pre-trained language models.

Expanding natural instructions

Beyond the Imitation Game collaborative benchmark for enormous language models