jianggy

lexical_elaboration

lingOly

A benchmark for language models based on the UK Linguistics Olympiad

asl-efficiency

American Sign Language Handshapes Reflect Pressures for Communicative Efficiency (ACL 2024)

RVP

Recursive Visual Programming

ReBase

ReBase: Training Task Experts through Retrieval Based Distillation

pyvene

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

arc_draw_more_samples_pub

Draw more samples

phonesthemes

Code for the paper "Discovering Phonesthemes with Sparse Regularization", to be presented at the NAACL 2018 Workshop on Subword and Character Level Models in NLP.

KinDiv

Lexical gap database in kinship domain

asjp

CLDF dataset derived from Wichmann et al.'s "ASJP Database"

evaluation-pipeline-2024

The evaluation pipeline for the 2024 BabyLM Challenge.

MultiDimensionalFeatures

Code for reproducing our paper "Not All Language Model Features Are Linear"

Memoirs-and-Thoughts

tuned-lens

Tools for understanding how transformer predictions are built layer-by-layer

Ag2Manip

Code Repository for "Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations"

OpenHowNet

Core Data of HowNet and OpenHowNet Python API

flashtext

Extract Keywords from sentence or Replace keywords in sentences.

EasyOCR

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

llama3

The official Meta Llama 3 GitHub site

gdrive

Google Drive CLI Client

Tac-Man-Simulation

Simulation studies for research "Tac-Man: Tactile-Informed Prior-Free Manipulation of Articulated Objects".

AOCHILDES

Python API for loading language data from American-English CHILDES database

faiss

A library for efficient similarity search and clustering of dense vectors.

MUSE

A library for Multilingual Unsupervised or Supervised word Embeddings

dreamcoder

online-unsup-proto-net

EISEN

video-models

Menagerie of video models trained on various video datasets

Baby-CoThought

Baby's CoThought: Leveraging LLMs for Enhanced Reasoning in Compact Models

one-api

OpenAI 接口管理 & 分发系统，支持 Azure、Anthropic Claude、Google PaLM 2 & Gemini、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑以及腾讯混元，可用于二次分发管理 key，仅单可执行文件，已打包好 Docker 镜像，一键部署，开箱即用. OpenAI key management & redistribution system, using a single API for all LLMs, and features an English UI.