Open-source alternatives to Promptsource

This project is a comprehensive technical interview study resource designed to help developers prepare for engineering job assessments. It functions as a structured guide that curates essential computer science fundamentals, web development standards, and programming language concepts into a format optimized for professional evaluation. The repository distinguishes itself by providing strategic guidance on architectural decision-making and professional communication. Beyond simple question-and-answer pairs, it offers frameworks for articulating experience during interviews and suggests profes

LMQL is a programming language and probabilistic interface that blends algorithmic logic with stochastic text generation. It functions as a constraint-guided prompting framework and structured output generator, allowing users to force model responses to adhere to strict formatting and data types. The system distinguishes itself as an inference optimizer that increases token throughput and reduces latency. This is achieved through specialized execution strategies, including tree-based prompt caching and asynchronous batch processing. The project covers a broad range of generation control capa

Metaseq is a transformer sequence modeling toolkit designed for training, fine-tuning, and deploying sequence-to-sequence models using open pre-trained weights. It provides a comprehensive framework for large language model training, including dedicated tools for sequence dataset processing and a standalone inference server for generating text via API requests. The project features specialized utilities for model quantization to reduce parameter precision to eight bits, which lowers memory usage and increases inference speed. It also includes a checkpoint conversion pipeline to transform mode

Original Flan (2021) | The Flan Collection (2022) | Flan 2021 Citation | License

This is a machine learning framework for treating diverse natural language processing tasks as a unified text-to-text problem. It provides a toolkit for pre-training and fine-tuning large-scale transformer models, utilizing a system where both inputs and outputs are formatted as raw text sequences. The framework is distinguished by its distributed training system, which uses mesh-based strategies to scale model weights and training batches across multiple TPU cores. It supports multi-task learning by combining diverse datasets into a single training stream using configurable mixture rates, al

🤗 HF Repo 📄 Paper 📚 6K Data 📚 10K Data

An open-source visual programming environment for battle-testing prompts to LLMs.

OpenChat is a framework for the training, fine-tuning, and deployment of large language models optimized for conversational and mathematical reasoning tasks. It provides a comprehensive lifecycle for these models, ranging from training pipelines and deployment stacks to a web-based chat interface. The project focuses on enabling high-performance model execution on consumer-grade hardware without the need for enterprise-grade accelerators. It includes a production-ready inference server that implements the OpenAI chat completion protocol and utilizes dynamic request batching to optimize hardwa

🎩 Models | 📚 Dataset | 🚀 Quick Start | 👀 Demo | 📝 Citation | 🙏 Acknowledgements

:black_heart: Create and share beautiful images of your prompts

Semantic Versioning for Prompts - Clear, predictable version management specification for AI prompts | Prompt 语义化版本规范

Towards Robust Grounded Language Modeling [DEMO](https://huggingface.co/spaces/luohy/SAIL-7B) | [WEB](https://openlsr.org/sail-7b)

A library for helping developers craft prompts for Large Language Models

New Release We released Adversarial training for both LM pre-training/finetuning and f-divergence.

Official Code Repository for the paper Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-intensive Tasks (NeurIPS 2023).

WizardLM is a large language model and instruction-tuning framework designed to execute sophisticated coding, mathematical, and conversational tasks. It functions as an AI system for mathematical reasoning and code generation, as well as a synthetic dataset generator used to train other language models. The project is distinguished by its evolutionary instruction tuning, which uses a method to rewrite simple instructions into complex tasks. This process expands training dataset difficulty and produces a high volume of open-domain tasks across various difficulty levels. The system covers capa

This repo introduces ExpertLLaMA, a solution to produce high-quality, elaborate, expert-like responses by augmenting vanilla instructions with specialized Expert Identity description. This repo contains: - Brief introduction on the method. - 52k Instruction-Following Expert Data generated by…

This repository contains the Unnatural Instructions dataset. Unnatural Instructions is a dataset of instructions automatically generated by a Large Language model. See full details in the paper: "Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor"

Promptfoo is an evaluation framework designed for testing, benchmarking, and red-teaming language models and agentic workflows. It provides a unified environment to run prompts against multiple providers, allowing developers to systematically validate model outputs against objective assertions, semantic similarity metrics, and custom grading rubrics. The platform distinguishes itself through a provider-agnostic execution layer and a stateful orchestrator capable of simulating multi-turn conversations and complex tool-use trajectories. It includes a dedicated adversarial mutation pipeline that

Exact structure out of any language model completion.

This repository contains the source code for reproducing the data curation of MUFFIN (Multi-faceted Instructions).

This is the repo for the Code Alpaca project, which aims to build and share an instruction-following LLaMA model for code generation. This repo is fully based on Stanford Alpaca ,and only changes the data used for training. Training approach is the same.

DSPy is a declarative programming framework designed for building complex language model applications. It treats model interactions as modular, composable programs, allowing developers to define task logic through typed class schemas rather than relying on manually written prompts. By organizing workflows into hierarchical, reusable Python objects, the framework enables the construction of sophisticated AI systems that manage state and execution flow independently. The framework distinguishes itself through an automated optimization engine that iteratively refines prompt instructions and few-

OpenPrompt is a prompt learning framework designed to adapt large language models to downstream natural language processing tasks. It provides a comprehensive toolkit for implementing manual, soft, and continuous prompting strategies, allowing models to be refined without updating all underlying parameters. The project is distinguished by its support for both discrete and continuous prompt tuning. It includes a system for injecting trainable soft tokens and embeddings into model inputs via gradient descent, as well as an automatic prompt generation engine that uses beam search and generative

UltraChat is a collection of large-scale conversational datasets and instruction-tuning data designed for training and evaluating generative AI models. It provides structured JSON data consisting of complex, multi-round dialogue sequences intended to refine the performance of large language models in chat tasks. The project focuses on improving reasoning and response quality through a diverse set of interactions across multiple sectors. These datasets are used for supervised fine-tuning and instruction tuning workflows to improve how models follow complex directions and maintain context acros