coolboyzk的博客

Running DeepSeek-R1 reasoning model using Ollama on an Ubuntu single board computer.

Introducing DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-world vision and language understanding applications. DeepSeek-VL possesses general multimodal understanding capabilities, capable of processing logical diagrams, web pages, formula recognition, scientific literature, natural images, and embodied intelligence in complex scenarios.

Deepseek-Go is a Go-based API client for the Deepseek platform. It provides a clean and type-safe interface to interact with Deepseek's AI features, including chat completions with streaming, token usage tracking, and more.

EasyMocap is an open-source toolbox for markerless human motion capture and novel view synthesis from RGB videos. In this project, we provide a lot of motion capture demos in different settings.

The entire training process of DeepSeek R1 is nothing but using different way of reinforcement learning on top of their base model (i.e. deepseek V3). To make everything easy to understand we will use hand drawn flowcharts along with the code and will follow the step by step implementation of deepseek technical report and will build our own model using a tiny base model that you can also run locally. We will also be covering theory next to each step, so in case you are not aware of DeepSeek R1.

This repository contains a powerful coding assistant application that integrates with the DeepSeek API to process user conversations and generate structured JSON responses. Through an intuitive command-line interface, it can read local file contents, create new files, and apply diff edits to existing files in real time.

官方认证的DeepSeek VL2源代码， 帮助您更好的理解DeepSeek的深层意义。