Code and data for Natural Language Processing Demystified

A framework for few-shot evaluation of language models.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Run evaluation on LLMs using human-eval benchmark

A system for prompted weak supervision. Alfred is a powerful tool that leverages large language models to accelerate data annotation.

Having fun with ML

A repository of Python scripts to scrape code contents of the public repositories of `huggingface`.