blog: add DeepSeek R1 local installation guide #4552
Conversation
chore: sync 0.5.14 release into main
- Add comprehensive guide for running DeepSeek R1 locally - Include step-by-step instructions with screenshots - Add VRAM requirements and model selection guide - Include system prompt setup instructions
|
Preview URL: https://6d249026.docs-9ba.pages.dev |
| @@ -0,0 +1,109 @@ | |||
| --- | |||
| title: "Beginner's Guide: Run DeepSeek R1 Locally (Private)" | |||
|
|
||
|  | ||
|
|
||
| You can run DeepSeek R1 on your own computer! While the full model needs very powerful hardware, we'll use a smaller version that works great on regular computers. |
There was a problem hiding this comment.
The flow of this first sentence is a bit off. I would recommend adding something along the lines of: "R1 is one of the best open source models in the market right now, and the best part is that we can run different versions of it on our laptop."
| Keep reading for a step-by-step guide with pictures. | ||
|
|
||
| ## Step 1: Download Jan | ||
| [Jan](https://jan.ai/) is a free app that helps you run AI models on your computer. It works on Windows, Mac, and Linux, and it's super easy to use - no coding needed! |
There was a problem hiding this comment.
I would recommend using words like "straightforward" instead of easy, super easy, or simple.
| <Callout type="info"> | ||
| 💡 Not sure how much VRAM your computer has? | ||
| - Windows: Press Windows + R, type "dxdiag", press Enter, and click the "Display" tab | ||
| - Mac: Click Apple menu > About This Mac > More Info > Graphics/Displays |
| - Mac: Click Apple menu > About This Mac > More Info > Graphics/Displays | ||
| </Callout> | ||
|
|
||
| Below is a detailed table showing which version you can run based on your computer's VRAM: |
There was a problem hiding this comment.
I would recommend adding a bit of wording on what is a distilled model versus the full one and why these say qwen vs llama. A lot of people won't know and are assuming they are downloading the original one.
| @@ -0,0 +1,188 @@ | |||
| --- | |||
| title: "How to run AI models locally: A Complete Guide for Beginners" | |||
|
This is the build for this pull request. You can download it from the Artifacts section here: Build URL. |
|
This is the build for this pull request. You can download it from the Artifacts section here: Build URL. |
|
This is the build for this pull request. You can download it from the Artifacts section here: Build URL. |
|
This is the build for this pull request. You can download it from the Artifacts section here: Build URL. |
|
|
||
| # How to run AI models locally: A Complete Guide for Beginners | ||
|
|
||
| Running AI models locally means installing them on your computer instead of using cloud services. This guide shows you how to run open-source AI models like Llama, Mistral, or DeepSeek on your computer - even if you're not technical. |
There was a problem hiding this comment.
You don't install them like an app, you download models to be consumed by a program. Maybe rewording this a bit here would be helpful.
I think it would sound much better, "regardless of your background" rather than "even if you're not technical."
|
|
||
| ## Understanding Local AI models | ||
|
|
||
| Think of AI models like apps - some are small and fast, others are bigger but smarter. Let's understand two important terms you'll see often: parameters and quantization. |
There was a problem hiding this comment.
I wouldn't compare them to apps since a lot of people don't know the difference between a GPT-4o and ChatGPT. The app and the model are already the same for them. Maybe the model is the engine and the app is the car chassis?
| ### 2. Use Hugging Face: | ||
|
|
||
| <Callout type="warning"> | ||
| Important: Only GGUF models will work with Jan. Make sure to use models that have "GGUF" in their name. |
There was a problem hiding this comment.
I think it would be useful to say a sentence or two on what is the GGUF format in the previous section on quantization.
|
This is the build for this pull request. You can download it from the Artifacts section here: Build URL. |
|
This is the build for this pull request. You can download it from the Artifacts section here: Build URL. |
Describe Your Changes
Fixes Issues
Self Checklist