Offline DeepSeek-R1 Tutorial

₹600-1500 INR

Completed

Posted 7 days ago

₹600-1500 INR

Paid on delivery

I need a concise, hands-on recorded screen-share (about two hours) that walks me through every step needed to run DeepSeek-R1-Distill-Qwen-1.5B from Hugging Face entirely on my own machine with no internet connection after setup. Windows or Linux is fine; I’ll mirror whatever you use. Key points I must see in the session: • Pulling the model and all dependencies locally (transformers, bitsandbytes, sentencepiece, etc.) so it can start and respond completely offline. • Training or fine-tuning it with either freely available or paid Hindi datasets—my main focus—showing at least one practical example (LoRA, QLoRA or another lightweight approach is acceptable). • Injecting both personality instructions and safety / content restrictions into the prompt-engineering or system-message layer, with an explanation of pros and cons of each method. • Advice on further quantisation beyond current levels (e.g., 4-bit, GGUF for [login to view URL]) and how that will affect speed versus accuracy. By the end I expect to have: 1. A working local inference script that loads the model offline. 2. A short notebook or script demonstrating Hindi fine-tuning on a sample dataset. 3. Clear notes or a cheat-sheet summarising the commands we ran, configuration files, and any links referenced. The live session can be recorded; please share the recording and all demo files immediately afterward so I can reproduce each step on my side without assistance.

Machine Learning (ML)

Natural Language Processing

Project ID: 40465023

About the project

2 proposals

Remote project

Active 7 days ago

Looking to make some money?

Email address

Benefits of bidding on Freelancer

Set your budget and timeframe

Get paid for your work

Outline your proposal

It's free to sign up and bid on jobs

Awarded to:

@likhithi

Hi, This is something I can help you with. I've worked with local AI model setups and understand the challenges of getting everything running completely offline. For this project, I'll record a step-by-step session showing the entire process, from downloading DeepSeek-R1-Distill-Qwen-1.5B and its dependencies to running inference without any internet connection. I'll also demonstrate a Hindi fine-tuning example using a lightweight approach such as LoRA/QLoRA, explain the training workflow, and show how to save and reuse the results locally. I'll cover different ways to add personality instructions and safety restrictions, including prompt-based and system-level approaches, along with the trade-offs of each method. I'll also walk through quantization options such as 4-bit loading and GGUF/[login to view URL] so you can understand the balance between memory usage, speed, and response quality. After the session, you'll receive the recording, inference script, fine-tuning example, and a concise cheat sheet containing the commands, configurations, and resources used during the demonstration. My goal is to make sure you can reproduce everything independently on your own machine without needing additional support afterward. I'd be happy to discuss your preferred OS (Windows or Linux) and tailor the walkthrough accordingly. Best regards, Likhith

₹800 INR in 3 days

0.0

(0 reviews)

0.0

2 freelancers are bidding on average ₹820 INR for this job

@serviceaxisgroup

Hi, I can help with a fully offline, recorded tutorial that gets DeepSeek-R1-Distill-Qwen-1.5B running on your machine and produces a working inference script plus Hindi fine-tuning demo. I’ll start by matching your OS and GPU/VRAM, then preparing a step-by-step flow that downloads once and caches transformers/bit/bitsandbytes/sentencepiece locally so it can respond with no internet. I’ll reduce risk by building a reproducible, review-friendly checklist of the exact commands, configs, and verification checkpoints. Do you use Windows or Linux, and what GPU/VRAM do you have? Also, should the Hindi example use QLoRA or LoRA? Once you answer, I’ll schedule the 2-hour screen share and send the materials immediately afterward.

₹840 INR in 3 days