[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Grok open release

Data and tools for generating and inspecting OLMo pre-training data.

Sample, estimate, aggregate: A recipe for causal discovery foundation models

Create LLM agents with long-term memory and custom tools 📚🦙

Code for fine-tuning Platypus fam LLMs using LoRA

Channel Vision Transformers: An Image Is Worth C x 16 x 16 Words

Contextual Vision Transformers for Robust Representation Learning

Contextual Vision Transformers for Robust Representation Learning

OneDiff: An out-of-the-box acceleration library for diffusion models.

Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

Deep universal probabilistic programming with Python and PyTorch

Tensorflow implementation of Invariant Rationalization

Tensorflow implementation for the Class-wise Selective Rationalization

BERT for Coreference Resolution

[ICLR'19] Meta-learning with differentiable closed-form solvers

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral

Code for "Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer"

A general-purpose neural semantic parser for mapping natural language queries into machine executable code

Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"

Intuitive Annotation Tool for Information Extraction / Named Entity Recognition using localturk / Amazon Mechanical Turk

This repo is for the IBM MIT AI Lab to use DLaaS in IBM Watson Studio. The demo will use Pytorch to train VGG for CIFAR10. The code is forked from kuangliu (https://github.com/kuangliu/pytorch-cifa…

A beautiful, simple, clean, and responsive Jekyll theme for academics

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

A TensorFlow implementation of DeepMind's WaveNet paper

Speedy Wavenet generation using dynamic programming ⚡