Sea-Snell

Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"

Sea-Snell

Official code for the paper "Context-Aware Language Modeling for Goal-Oriented Dialogue Systems"

Sea-Snell

unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"

Sea-Snell

Train very large language models in Jax.

Sea-Snell