Datawhale 开源项目管理委员会（Datawhale Open-source Project Management Committee，简称DOPMC）
Mr. Ranedeer AI Tutor is an AI education framework and system prompt designed to transform a large language model into a personalized tutor. It uses a structured set of instructions to organize educational content into sequential modules and knowledge assessments for adaptive learning. The system features a persona template that allows for the adjustment of academic depth and communication tone to match a student's specific needs. It also provides multilingual support, enabling the tutor to switch instruction and output languages based on user preferences. The framework covers custom lesson
Prompt Optimizer is a framework designed for the iterative refinement and testing of text-based instructions for large language models. It functions as an automated evaluation pipeline that systematically adjusts prompt structure, constraints, and clarity to improve the accuracy and consistency of model outputs. The system distinguishes itself through a model-agnostic interface that standardizes communication across different artificial intelligence providers. It incorporates a versioned asset management system to track prompt history, enabling developers to maintain consistency and perform r
Unofficial implementation and experiments related to Set-of-Mark (SoM) 👁️
The main features of skalskip/som are: Foundational AI References.
Open-source alternatives to skalskip/som include: datawhalechina/dopmc — Datawhale 开源项目管理委员会（Datawhale Open-source Project Management Committee，简称DOPMC）. en/get-started. jushbjj/mr.-ranedeer-ai-tutor — Mr. Ranedeer AI Tutor is an AI education framework and system prompt designed to transform a large language model into… linshenkx/prompt-optimizer — Prompt Optimizer is a framework designed for the iterative refinement and testing of text-based instructions for large… rryuliu/securitygpt. significant-gravitas/auto-gpt — Auto-GPT is an autonomous agent framework that uses large language models to decompose complex goals and execute…