Stars
Analyze experimental data with Programming by Navigation
TWIX is an open-source data extraction tool that reconstructs structured data from documents at scale, accurately and at low cost, by inferring the shared underlying visual template across documents
Welcoming contributions from practitioners building AI/data systems - share your real-world problems, document where current tools fail, and help improve the benchmark taxonomy across the enterpris…
Optimize prompts, code, and more with AI-powered Reflective Text Evolution
Interactive Debugging for Retrieval Augmented Generation Pipelines
Two conversational AI agents switching from English to sound-level protocol after confirming they are both AI agents
METIS - Serial Graph Partitioning and Fill-reducing Matrix Ordering
A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.
Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators (Liu et al.; COLM 2024)
A system for agentic LLM-powered data processing and ETL
multilspy is a lsp client library in Python intended to be used to build applications around language servers.
Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.
Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to…
Automatic Generation of Visualizations and Infographics using Large Language Models
Automatically visualize your pandas dataframe via a single print! 📊 💡
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…
A toy superoptimizer for a limited assembly language.
Data Wrangler extension for Visual Studio Code
Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch
Clone a voice in 5 seconds to generate arbitrary speech in real-time
CAL Interpreter powered by GraalVM
Simple react application to create a TimeTable based only on your choice of subjects.
Hosted at @covidreliefbot on Telegram