jcwhuang

cs224w-project

Final project for CS224W at Stanford University, Autumn 2015

dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

batch_rl

Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games

cs221-project

LoRA

Code for "LoRA: Low-Rank Adaptation of Large Language Models"

naive-twitter-tagger

Naive Bayes Classifier that "classifies" tweets by predicting "relevant" hashtags (originally Intro to Machine Learning final project)

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.