Articles by Yang Fan

Step 1: Install the "magic tool" Ollama 🚀 (Windows computers look here!) What is Ollama? 🤔 Again, Ollama is a "magic toolkit" that makes it easy to run awesome AI models like DeepSeek, which we'll be using today, and which makes AI models work like electricity...

Running DeepSeek-R1 with an RTX 4090 graphics card, it is recommended to prioritize the 671B full-blooded version of the Q4_K_M quantization, followed by the 14B or 32B quantization version, provided that it relies on KTransformers, and if it is a pain in the ass to learn, you can go for the quantization version put out by Unsloth, and there is also a tutorial for installing Ollama here Deep...

First, does 360 access DeepSeek? The answer is yes. 360 Group announced in January 2025 that it would provide network security protection for DeepSeek free of charge, and opened a DeepSeek high-speed private line in its product "Nano AI Search". The dedicated line guarantees the stability of the service through national security capabilities and dedicated server rooms....

First, the core positioning of the relationship between the two parties According to public information, 360 and DeepSeek have not established a direct equity relationship or traditional business cooperation, but there is an indirect association of technical synergy and strategic support. For example, 360's Nano AI Search APP integrates 16 domestic large models including DeepSeek-R1, and users can...

Yes, 360's "Nano AI Search" does have a PC version, and you can use DeepSeek-R1 full-blooded version for free! 1. official PC client has been online According to the 360 official release, February 11, 2025 release of the "nano AI" Windows desktop version of the client, built directly into the DeepSeek-R1 networking full-blooded version (671B parameter ...

360 DeepSeek and the original version of the difference Here from the functional positioning, the actual performance, technical differences between the three perspectives to help you sort out the difference, after you know how to choose 👇 First, the functional positioning of the different original DeepSeek: divided into two "brain" to work V3 model (default): like a "universal toolbox" to write articles, translations. V3 model (default): like an "all-purpose toolbox" for writing articles, translating...

First, the official entrance and download 360 Nano Search App (recommended) Download address: search for "Nano Search" in the app store or visit Nano AI Search. Function Description: Integrated DeepSeek-R1-360 high-speed dedicated line, fast response time and free. Support switching other AI models (e.g., Doubao, Wenxin Yiyin)...

Analysis of Hardware Requirements for Local Deployment of DeepSeek Models Analysis of Core Hardware Elements The hardware requirements for model deployment mainly depend on three dimensions: Parameter magnitude: 7B/67B and other models of different sizes vary greatly in terms of video memory requirements, and the largest DeepSeek R1 671B Tutorials for Local Deployment: Based on the Ollama and Dynamic Measurement...

The core of the problem is not deepseek, there is no difference between deepseek and other big model usage techniques, you can learn a lot of usage techniques in AI commands, about deepseek-specific techniques, you should know that DeepSeek-r1 belongs to the inference model, by his specific usage techniques, e.g.: OpenAI publishes...

I. Impact and Challenge: Reconstruction of Brick-and-Mortar Traffic and Price System Basic Consultation Substitution and Price Transparency DeepSeek may accelerate the loss of low-value traffic in brick-and-mortar stores by lowering the threshold for consumers to access professional information. For example, in the pharmaceutical retail sector, consumers can quickly access medication advice through AI assistants...

When building a RAG system, choosing the right Embedding model is a crucial step, here are my key factors and suggestions to consider when choosing an Embedding model for your reference: Clarify the application scenario First of all, it is necessary to clarify the specific application scenarios and requirements of the RAG system. For example, is the processing of text...