NYU Deep Learning Spring 2021

Train transformer language models with reinforcement learning.

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

Efficient Infinite Context Transformers with Infini-attention Pytorch Implementation + QwenMoE Implementation + Training Script + 1M context keypass retrieval

EyetrackingAugmentedTransformers

The code will be released for the paper "Gaze-infused BERT: Do Human Gaze Signals Help Pre-trained Language Models?"

A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.

Practical course about Large Language Models.

Original Implementation of Prompt Tuning from Lester, et al, 2021

Language Generation from Brain Recordings

Repo for EMNLP finding Paper "Long-Range Language Modeling with Selective Cache"