Articles by Yang Fan

Comprehensive Introduction ModelScope Swift (MS-Swift for short) is an efficient lightweight infrastructure designed for fine-tuning, reasoning, evaluating, and deploying large models (LLMs) and multimodal large models (MLLMs). The framework supports over 400 LLMs and 100+ MLLMs, providing everything from model training, evaluation...

General Introduction LLaMA-Factory is a unified and efficient fine-tuning framework that supports flexible customization and efficient training of more than 100 large language models (LLMs). Through the built-in LLaMA Board web interface, users can fine-tune their models without writing code. The framework integrates a variety of advanced training...

Introduction The Query Transformations User Manual demonstrates a variety of techniques for transforming and disambiguating user queries before they are executed in a Retrieval-Augmented Generation (RAG) query engine, intelligences, or other processes. These transformations can improve the quality and relevance of responses in AI applications. https://github.com/adithya-s-k/AI-...

General Description Hoarder is a self-hosted bookmark management tool that supports storage of links, notes, PDFs and images. It utilizes AI technology for automatic tagging and provides full-text search capabilities. Users can quickly add bookmarks via the Chrome plugin and Firefox plugin, and it also supports iOS and An...

A spokesperson for OpenAI has issued an official statement in response to the incident. The statement mentioned that the Sora model is still in the "research preview" phase and that the company is trying to balance creativity with strong security measures so that the technology can be used more widely in the future, and OpenAI emphasized that participation in the...

Since yesterday's release of Anthropic's open-source Model Context Protocol: Model Context Protocol (MCP), which according to Anthropic, Block, and Apollo has been integrated into their systems, Replit, Codeium, and Sourcegraph...

It's like being a smart kid who doesn't understand coding best practices. You need to tell the AI exactly what you want: is it a web application? What functionality is needed? What is the structure? And so on. Here's how to make AI your full-stack developer: Context is critical! You need to...

Comprehensive Introduction aisuite is a simple, unified interface designed to allow developers to easily invoke the services of multiple generative AI providers. With an interface similar to OpenAI, aisuite makes it easier to interact with the most popular LLMs (Large Language Models) and to do so without changing the code...

  Video Summary [00:00:04] - Anthropic MCP is a new standard for connecting AI assistants to systems where data resides. [00:00:17] - Anthropic MCP provides a common open standard for connecting AI systems to data sources. [00:00:28] - MCP has...

Comprehensive Introduction PlayAI is an artificial intelligence platform focused on speech generation and speech cloning. It provides a wide range of speech models capable of generating smooth and emotional dialog. Users can use the platform to create personalized voice agents to enhance the interactive experience.PlayAI's technology is suitable for a variety of applications...

There was this junior high school student who launched a project in the second semester of his first year dedicated to giving his friends a free experience with the GPT-4 model. By the summer of 8th grade, he decided to open source the project and officially named it Chat Nio, while positioning the project as a one-stop LLM model management platform...

Introduction Thomas joined Vespa in April 2024 as a Senior Software Engineer. In one of his last previous assignments as an AI consultant, he actually built a RAG application based on Vespa's massive PDF collections. PDFs are ubiquitous in the corporate world, and searching and retrieving from them...

Comprehensive introduction pdf2htmlEX is an open source tool designed to convert PDF files to HTML format , by analyzing the content of PDF files and use HTML + CSS to accurately restore its visual effect , PDF documents into a browser can be viewed directly on the web page . The tool is particularly suitable for containing a large number of ...

General Introduction Higress is a cloud-native API gateway developed by Alibaba, built on Istio and Envoy, designed to provide efficient traffic scheduling, service governance and security solutions. It supports Wasm plugin extensions for multiple programming languages for AI business, microservices and Kubernetes Ingre...

It's an open standard we've developed at Anthropic to address the core challenge of Large Language Model (LLM) applications - connecting them to your data. There's no need to build custom integrations for each data source.MCP provides one protocol for connecting all your data sources: Here's what you can do with Cla...

Introduction Self-Query RAG (SQRAG) is an advanced Retrieval Augmented Generation (RAG) approach that enhances the traditional RAG process by introducing metadata extraction in the ingestion phase and intelligent query parsing in the retrieval phase. https://github.com/adithya-s-k/AI-Engi...

General Introduction CodeGPT is an AI programming assistant platform designed for developers. It provides a variety of AI assistants and Copilot generation tools designed to simplify the programming process for engineering teams. Users can use Cod...