frankxu2004

knnlm-why

Repo for ICML23 "Why do Nearest Neighbor Language Models Work?"

cooking-procedural-extraction

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

knnlm-locality

Repo for ICLR22 "Capturing Structural Locality in Non-parametric Language Models"

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

awesome-social-agents

A collection of works that investigate social agents, simulations and their real-world impact in text, embodied, and robotics contexts.

Code-LMs

Companion Model for "A Systematic Evaluation of Large Language Models of Code"

CodeT5

Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

OpenDevin

🐚 OpenDevin: Code Less, Make More

tranX

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

AgentLab

ai-deadlines

:alarm_clock: AI conference deadline countdowns

AI-writer_Data2Doc

PyTorch Implementation of NBA game summary generator.

BrowserGym

BrowserGym, a gym environment for web task automation in the Chromium browser.

codelm-playground

data2text

DrQA

A pytorch implementation of Reading Wikipedia to Answer Open-Domain Questions.

efficient-knnlm

empirical-methods

Homepage for 17-803 "Empirical Methods" at Carnegie Mellon University

feedforward-RE

Feedforward NeuralNet for Relation Extraction

frankxu2004.github.io

graphgrove

A framework for building (and incrementally growing) graph-based data structures used in hierarchical or DAG-structured clustering and nearest neighbor search

kchar

Character-Aware Neural Language Models. A keras-based implementation

knn-transformers

PyTorch + HuggingFace code for RetoMaton: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022), including an implementation of kNN-LM and kNN-MT

Muskits

An opensource music processing toolkit

nextjs-starter-medusa

OpenNMT-py

Forked for data-to-text generation dev

ParallelWaveGAN

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

tacred-relation-cotrain

Position-aware attention model for relation extraction

XLM

PyTorch original implementation of Cross-lingual Language Model Pretraining.