Yesterday, I spent several hours deeply experiencing DeepSeek’s latest open-source multimodal model, Janus Pro. I must say, this model feels like a combination of a “top student” and a “poor performer”—it truly dazzles in image understanding but disappoints in text-to-image generation. Let’s take a closer look at the detailed performance of this “dual-natured” model. First … Read more
https://www.itdog.cn/http/ If you cannot directly download models from HuggingFace[1], you can use the https://github.com/AlphaHinex/hf-models repository and build a Docker image using GitHub Actions[2]. In the image, use huggingface_hub[3] to download the required models, then push the image to Docker Hub[4]. Finally, you can download the model using the image. 1Available Models (tags) Currently available models … Read more
Traefik: A New Choice for Reverse Proxy Hello everyone! Today I want to share a very cool tool – Traefik. As a developer who often works with containers, I deeply realize how important a good reverse proxy is in a microservices architecture. Traefik is like an intelligent traffic commander; it can not only automatically discover … Read more
This article discusses how to use Traefik with Docker containers for stable deployment of Traefik services. Introduction It has been nearly four years since the release of Traefik v2.0.0[1]. Over the past four years, I have written extensively about practical content related to Traefik, which interested readers can explore here[2]. Last month, the official release … Read more
There’s something a bit hard to say. Actually, I’ve been using Baidu’s homepage navigation feature for over a decade, which is this thing: Image from the internet Because hao123 is too flashy, and as a long-time Tieba user, using Baidu’s navigation is indeed more convenient. After years of using it, I have accumulated over a … Read more
Introduction ChatGPT is incredibly powerful! OpenAI’s CEO Sam Altman stated directly: this is our most powerful model to date! It performs comparably to humans on various professional and academic benchmarks! It must be said that since the launch of ChatGPT, Microsoft has won several rounds in the tech battle against Google. This article introduces an … Read more
This article introduces how to use Python, PhiData, FastAPI and Docker to build a simple AI Agent, and expose it as a Web service. Main Points Using PhiData to build a simple AI Agent, which decides whether to turn on the heater or air conditioning based on temperature. Using FastAPI to create a RESTful API, … Read more
Purpose: Establish your own workflow through Dify to enhance personal AI capabilities. Goal: Implement Dify’s Docker container locally to build your own workflow. This article focuses solely on the deployment and installation of Dify. First, let’s have a look at the origin of the name Dify: Do It For You Official Dify GitHub address: https://github.com/langgenius/dify … Read more
Introduction Do you want to run large language models locally and create your own AI assistant? The latest Ollama 0.5.7 version makes this easier than ever. By following the steps below, you will easily complete the deployment and embark on an intelligent journey!💡 🎯 What is Ollama? Ollama is a tool designed to help users … Read more
Deploying DeepSeek Large Model Using Ollama Prerequisites Download CUDA drivers using NVIDIA graphics card https://developer.nvidia.com/cuda-downloads Ollama Ollama Official Version: https://ollama.com/ My graphics card is on a Windows computer, so I will install using the Windows installation method.If your graphics card is on Linux, you can install using the following command. curl -fsSL https://ollama.com/install.sh | sh … Read more