bytedance/deer-flow
DeerFlow is a community-driven deep research framework that integrates language models with web search, crawling, and Python execution tools to facilitate comprehensive AI-powered research workflows.
Awesome AI Agents › Reasoning Frameworks
ystemsrx/Qwen2-Boundless
Qwen2-Boundless is an advanced language model fine-tuned from the Qwen2-1.5B-Instruct model, designed to handle a wide range of questions including sensitive and controversial topics such as violence, explicit content, illegal activities, and unethical behavior. This model is versatile, capable of responding to both conventional and controversial queries, making it suitable for diverse applications. It is primarily optimized for Chinese language tasks, reflecting the nature of its training datasets. The fine-tuning process utilized specialized datasets including Bad_Data.json, which contains content related to sensitive topics, and a dataset derived from Clouditera/SecGPT focusing on cybersecurity issues. The fine-tuning was conducted using the LLaMA-Factory framework, ensuring a robust and efficient training process. The project is open-sourced and available on Hugging Face, providing accessibility for research and development purposes. Usage examples are provided through scripts demonstrating basic usage, continuous conversation, and streamed output, facilitating easy integration and experimentation. The model is intended for research purposes only, with a clear disclaimer advising users to apply it in controlled environments and comply with legal and ethical standards. The creators do not endorse any illegal or unethical use of the model. Licensed under Apache 2.0, the project acknowledges contributions from the original Qwen2-1.5B-Instruct developers, the LLaMA-Factory project, and dataset contributors. Overall, Qwen2-Boundless represents a significant effort to create a language model capable of addressing complex and sensitive topics responsibly while maintaining versatility for general use.
https://github.com/ystemsrx/Qwen2-Boundless
Also in Reasoning Frameworks
VectifyAI/PageIndex
PageIndex is a reasoning-based document indexing and retrieval system that uses a hierarchical tree structure to enable human-like, vectorless retrieval and multi-step reasoning over long professional documents.
guidance-ai/guidance
Guidance is a programming paradigm and library that enables efficient and fine-grained control over large language models to produce structured, high-quality outputs with reduced latency and cost.
friuns2/BlackFriday-GPTs-Prompts
A curated repository of free GPT prompts and jailbreaks across various domains, enabling users to utilize GPT models without a subscription to GPT Plus.
refly-ai/refly
Refly is an open-source AI-native creation engine that combines multi-threaded dialogues, multimodal inputs, knowledge base integration, and AI-powered tools to transform ideas into production-ready interactive content and web applications.
mongodb-developer/GenAI-Showcase
MongoDB's GenAI Showcase is a comprehensive repository offering examples and applications that integrate MongoDB with advanced Generative AI techniques like Retrieval-Augmented Generation and AI Agents to support AI development and innovation.
anysphere/priompt
Priompt is a JSX-based prompting library that uses a priority system to efficiently construct token-limited prompts for language models, inspired by React's component design.
HKUDS/Auto-Deep-Research
Auto-Deep-Research is an open-source, fully automated, and cost-effective personal AI assistant that supports multiple large language models and offers a one-click launch experience as an alternative to OpenAI's Deep Research.