Official code for the paper "Context-Aware Language Modeling for Goal-Oriented Dialogue Systems"
MIT License
Embed arbitrary modalities (images, audio, documents, etc) into large language models.
A modular RL library to fine-tune language models to human preferences
Code for paper Fine-tune BERT for Extractive Summarization
A selection of 3D control scenarios created in a highly efficient simulator, benchmarked with the...
Official code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation
Solution to Project 1 of Udacity Deep Reinforcement Learning Nanodegree
Chain-of-Hindsight, A Scalable RLHF Method
We present NoticIA, a dataset consisting of 850 Spanish news articles featuring prominent clickba...
lint - Leveraging INTerpretability
TensorFlow Models for the Stanford Question Answering Dataset
PyGame-based quadcopter simulator & Reinforcement Learning Project
Fine-tuned LLaMa2 13B model designed for ReAct-style and Tree-Of-Thoughts style prompting.