Skip to content

Latest commit

 

History

History
92 lines (61 loc) · 3.24 KB

README.md

File metadata and controls

92 lines (61 loc) · 3.24 KB

Here's a detailed for setting up and running DeepSeek R1 locally with all the mentioned resources and instructions:

DeepSeek R1: Local Setup Guide

DeepSeek R1 is a powerful open-source AI model capable of performing reasoning, coding, and math tasks, comparable to OpenAI o1 and Claude 3.5 Sonnet. This guide will help you set up DeepSeek R1 locally on your machine for free and with complete privacy.

Step 1: Download and Install Ollama

Ollama is a tool for running AI models locally on your machine.

Download Ollama

Install Ollama

  • Follow the installation instructions based on your OS.
  • Example for installation:
    Installing Ollama

Step 2: Pull and Run the DeepSeek R1 Model

Choose Model Size

DeepSeek R1 offers multiple sizes based on your hardware capability:

  • 1.5B (Smallest): ollama run deepseek-r1:1.5b
  • 8B: ollama run deepseek-r1:8b
  • 14B: ollama run deepseek-r1:14b
  • 32B: ollama run deepseek-r1:32b
  • 70B (Largest): ollama run deepseek-r1:70b

Start with a smaller model to test performance.

Run the Command

Open your terminal and run the following command:

ollama run deepseek-r1:8b

Refer to the image for downloading progress:
Downloading DeepSeek

Download Progress

It will download the model. Wait until it reaches 100%:
Download Progress
Download Complete

Step 3: Install Chatbox

Chatbox is a clean, privacy-focused desktop interface for interacting with AI models.

Download Chatbox

Step 4: Configure Chatbox

  1. Open Chatbox and navigate to Settings.
  2. Set the Model Provider to Ollama.
  3. Configure the API Host to http://127.0.0.1:11434.

Refer to the image below for configuration details:
Chatbox Configuration

Step 5: Run the Model and Interact

  • After completing the setup, you can start interacting with the model via Chatbox.
  • Example of asking a question and receiving an answer:
    Model Interaction

Additional Notes

  • Ensure you have sufficient GPU resources for larger models (32B and 70B).
  • For any issues, check the logs in Ollama or the Chatbox troubleshooting guide.

Enjoy using DeepSeek R1 for your AI tasks! Let us know if you have any feedback or questions. 🚀