Microsoft Open Source

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.

All things prompt engineering

Prompt Orchestration Markup Language

Task-Aware Agent-driven Prompt Optimization Framework

Debugging, monitoring and visualization for Python Machine Learning and Data Science

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.

A library for helping developers craft prompts for Large Language Models

Graphormer is a general-purpose deep learning backbone for molecular modeling.

Scenarios, tutorials and demos for Autonomous Driving

AICI: Prompts as (Wasm) Programs