Starred repositories
Convert addresses to U.S. Census Block Group's Area Deprivation Index
"Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A frontier, first-principles handbook inspi…
A package to quickly visualise risk-of-bias assessment results
Large Language Model based Multi-Agents: A Survey of Progress and Challenges (In IJCAI 2024)
A python module to repair invalid JSON from LLMs
Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)
Code for the paper "Language Models are Unsupervised Multitask Learners"
A command-line interface for interacting with MCP (Model Context Protocol) servers using both stdio and HTTP transport.
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
Integrate the DeepSeek API into popular softwares
The twitter sentiment corpus created by Sanders Analytics, it consists of 5513 hand-classified tweets(however, 400 tweets missing due to the scripts created by the company). Each tweet was classifi…
Text-to-SQL Generation for Question Answering on Electronic Medical Records
ACL2023 - AlignScore, a metric for factual consistency evaluation.
Adding guardrails to large language models.
Magnificent app which corrects your previous console command.
Pyenv plugin to create a jupyter kernel for every installed pyenv version
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
A high-throughput and memory-efficient inference and serving engine for LLMs
Official implementation for ICML24 paper "Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach"
Code for the paper "Larger and more instructable language models become less reliable"