Sea-Snell

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

JAXSeq. Train very large language models in Jax.

JAX_llama. Inference code for LLaMA models in JAX

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

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

MLLibCpp. A machine learning library capable of training various deep neural networks (RNNs, LSTMs, DBNs, ect...) on a GPU. It makes use of auto-differentiation algorithms. Written in C++ with OpenCl.

micro_config. an opinionated config framework for deep learning based on hierarchical python dataclasses

jax_v_pytorch. comparing Jax (haiku and flax) to PyTorch on simple DL tasks.

170project. Jupyter Notebook

2d-procedural-endless-world. 2d procedural endless world

tpu_pod_launcher. Python

AttentionDynamics. Python

visdial-rl. PyTorch code for Learning Cooperative Visual Dialog Agents using Deep Reinforcement Learning

opticsSim. Simulator for the optics event in science olympiad division C

LMTemplate. Shell

cs183-283a-assignments-public. Jupyter Notebook