State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

Python wrapper of Android uiautomator test tool.

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API.

A GPT-J API to use with python3 to generate text, blogs, code, and more

A curated list of research papers and resources on Indonesian languages

Structured state space sequence models

The source code of "Language Models are Few-shot Multilingual Learners" (MRL @ EMNLP 2021)

Parallelformers: An Efficient Model Parallelization Toolkit for Deployment

A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling

Model parallel transformers in JAX and Haiku

Autoregressive Entity Retrieval

Continual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and other strategies.

Code base used for NLP project 2020.

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

A framework for few-shot evaluation of language models.

Pytorch library for fast transformer implementations

AutoPrompt: Automatic Prompt Construction for Masked Language Models.

A 🤗-style implementation of BERT using lambda layers instead of self-attention

KE-Dialogue: Injecting knowledge graph into a fully end-to-end dialogue system.

Code to reproduce experiments in the paper "Task-Oriented Dialogue as Dataflow Synthesis" (TACL 2020).

Neo4j graph visualization using D3.js

Meta-learning model agnostic (MAML) implementation for cross-accented ASR

Implementation of meta-transfer-learning for ASR and LM (ACL 2020)

Code for "Supermasks in Superposition"