Sérgio Giraldo sergiorgiraldo

DeepSeek R1 Distill: Complete Tutorial for Deployment & Fine-Tuning

This guide shows how to deploy an uncensored DeepSeek R1 Distill model to Google Cloud Run with GPU support and how to perform a basic, functional fine-tuning process. The tutorial is split into:

Environment Setup
FastAPI Inference Server
Docker Configuration
Google Cloud Run Deployment
Fine-Tuning Pipeline (Cold Start, Reasoning RL, Data Collection, Final RL Phase)

Git Cheat Sheet

Visit my blog or connect with me one Twitter

Commands

Getting Started

git init

or

	<!DOCTYPE html>
	<html>
	<head>
	<meta name="description" content="Iteration Samples - Ramda, Lodash, chaining, transducers">
	<script src="https://cdn.jsdelivr.net/g/lodash@4(lodash.min.js+lodash.fp.min.js)"></script>
	<script src="https://cdnjs.cloudflare.com/ajax/libs/ramda/0.25.0/ramda.js"></script>
	<script src="https://cdn.rawgit.com/zloirock/core-js/master/client/shim.min.js"></script>
	<script src="https://wzrd.in/standalone/tape@latest"></script>
	<script src="https://wzrd.in/standalone/tap-browser-color@latest"></script>
	<script src="https://wzrd.in/standalone/tape-catch@latest"></script>

	<!DOCTYPE html>
	<html>
	<head>
	<script src="http://code.jquery.com/jquery-1.9.1.min.js"></script>
	<script src="http://cdnjs.cloudflare.com/ajax/libs/ramda/0.7.2/ramda.js"></script>
	<script src="http://code.highcharts.com/highcharts.js"></script>
	<script src="http://code.highcharts.com/highcharts-3d.js"></script>
	<script src="http://code.highcharts.com/modules/exporting.js"></script>
	<meta charset="utf-8">
	<title>Ramdajs</title>