TRL v1.0: Post-Training Library Built to Move with the Field

Introducing the Private Hub: A New Way to Build With Machine Learning

The Transformers Library: standardizing model definitions

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders

Model internals encode rich information about how a large language model (LLM) processes its training data; however, post-training data engineering largely relies on external signals and ignores rich intrinsic signals lying in model internals. We propose SAERL, a data engineering framework for LLM reinforcement lear...

huggingface_hub v1.0: Five Years of Building the Foundation of Open Machine Learning

Train a Sentence Embedding Model with 1B Training Pairs

Accelerating discovery with the AI for Math Initiative

The initiative brings together some of the world's most prestigious research institutions to pioneer the use of AI in mathematical research.