Projects sharing features with Opro

This project is an automated prompt engineering and optimization tool designed to iteratively create, test, and refine prompts using a language model to improve output quality. It functions as a framework for generating candidate prompts and ranking their performance through correctness matching and ELO-based ratings. The system includes capabilities for model distillation, generating high-quality example pairs from frontier models to create training data for smaller models. It also provides tools to condense prompts for smaller models and transform instruction-tuned prompts into completion-b

auto-dev is an AI-native software engineering tool and multi-agent development platform designed to automate the entire software development lifecycle. It functions as an autonomous orchestrator that manages AI-driven coding, testing, and infrastructure configuration through declarative agent chains. The project is built on a Kotlin Multiplatform AI framework, allowing agent logic to run across diverse environments and device interfaces. The platform implements the Model Context Protocol to exchange tools and project information with external AI services. It distinguishes itself through the u

This repository is a comprehensive set of tutorials and examples for building software powered by large language models. It serves as an application development guide and a prompt engineering framework, providing instructional content for integrating model logic with user interfaces and external data sources. The project provides technical walkthroughs for specialized workflows, including the implementation of retrieval augmented generation using vector databases and semantic search. It includes guidance on adapting pre-trained model weights through fine-tuning with private datasets and the o

LMOps is a research-driven operations framework for optimizing the deployment, fine-tuning, and performance of large language models. It provides a specialized toolkit for foundation model adaptation, inference acceleration, prompt optimization, and context orchestration. The framework distinguishes itself through an inference accelerator that reduces token generation latency by verifying and copying overlapping text spans from reference documents. It also features a prompt engineering optimizer that employs reinforcement learning, beam search, and non-natural language markers to automaticall

#license-gh-package: https://lbesson.mit-license.org/ #arxiv-paper-package: https://arxiv.org/abs/2412.03092/ #pypi-package: https://pypi.org/project/revolve/

Authors: Archiki Prasad, Peter Hase, Xiang Zhou, and Mohit Bansal (UNC Chapel Hill) Paper Note: This is preliminary version of our code. The complete code to run all experiments in the paper will be added shortly.

Toolkits for discrete, black-box prompt learning based on metaheuristic algorithms.

This repo provides the source code & data of our paper: Unleashing the Potential of Large Language Models as Prompt Optimizers: An Analogical Analysis with Gradient-based Model Optimizers.

This is the implementation of the paper GPS: Genetic Prompt Search for Efficient Few-shot Learning. GPS is an automatic prompt search method based on genetic algorithm for better few-shot learning.

This is an implementation of the method proposed in

| 📄ICLR Spotlight | 🤗HF Paper | 📊Datasets | 🤖Models | 📧 Contact Us

This is the official repo for "PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization". PromptAgent is a novel automatic prompt optimization method that autonomously crafts prompts equivalent in quality to those handcrafted by experts, i.e., expert-level prompts.

This is the official implementation of the paper Prompt Optimization with Human Feedback.

This is the official implementation of the paper Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers, accepted by ICLR'2024.