Install and Set Up Ollama https://ollama.com/ After downloading and installing, it will automatically start with the system by default. The model is installed on the default system disk, so there is no need to set it to auto-start; you can start it whenever you want; then set the default installation path for the model. Delete … Read more
1. Basic Description 1. The models from ollama are all stripped-down versions. 2. They are relatively weak in distributed environments. 3. ollama is lightweight and suitable for individual users, but not for enterprise users. 4. ollama only performs model inference (used for running models). 5. ollama uses GGUF for quantization. 6. Engineering deployment generally does … Read more
Hello everyone, I am Sunbird! In this era of information explosion, how to efficiently manage and retrieve knowledge has become a challenge we all face. Today, I want to introduce you to an open-source project that has gained 4.6k stars on GitHub—Llama Index. Project Introduction: Llama Index is an AI-based knowledge management system that helps … Read more
1. Each large model framework has specific format requirements for its fine-tuning data. For example, LlamaFactory supports it, and you can refer to the documentation: https://llamafactory.readthedocs.io/zh-cn/latest/getting_started/data_preparation.html 2. Convert Ruozhiba data into LlamaFactory data format. import json # Conversion function def convert_format(original_data): converted_data = [] for item in original_data: converted_item = { "instruction": item["query"], "input": "", … Read more
Previously, I wrote an article about generating code using Deepseek, which was quite popular. Some people suggested using Windsurf instead, claiming it’s even more powerful than cursor. Others mentioned generating more complex code—like Tetris—to showcase the AI’s capabilities. So, let’s give Windsurf a try. This is an IDE released by Codeium last month, and you … Read more
▼Recently, there have been a lot of live broadcasts,make an appointment to ensure you gain something. The RAG (Retrieval-Augmented Generation) technology is detailed in the article “Understanding RAG: A Comprehensive Guide to Retrieval-Augmented Generation,” with a typical RAG case shown in the image below, which includes three steps: Indexing: Split the document library into shorter … Read more
1. Introduction Since leaving the last company with Yuanwai, we started our own company focusing on the development of RAG large model AI product applications. During this period, which included a Spring Festival, the total time was about three months. We worked day and night, and as of the end of March, the product has … Read more
“Your Majesty! Recently, I feel that my efficiency in writing backend code is low. I heard that Cursor is a magical tool that can help improve programming efficiency. Is that true?” The concubine asked with great anticipation. “Indeed. Cursor is like your personal programming assistant; it can not only help you write code quickly but … Read more
In-Depth Reveal: How Cursor Doubles Remote Development Efficiency “This broken code, I have to debug the environment for half a day…” Xiao Wang was complaining about the various difficulties of remote development. I interrupted him with a smile: “Let’s try Cursor, just install it and use it, it’s way better than your traditional IDE.” “Come … Read more
Today, I want to share an interesting development experience where, using Cursor, this magical AI coding assistant, we helped a programming novice rapidly develop a simple social application in just three hours. 1. Act One: Getting to Know Cursor “Your Majesty, I want to create a simple social application, but I only know a little … Read more