Source Code

I’m sharing the exact notebook I use so you can replicate the full pipeline: load DeepSeek R1 distilled, apply LoRA, run SFT, and export to Ollama. If you want a working baseline you can modify for your own dataset, this is the fastest way to get there. I prefer shipping code because fine-tuning details matter, and small mistakes can waste hours.

Buy on Github

You'll be taken to Github to complete your purchase.

ShareTwitter Facebook LinkedIn Instagram

Pros

+End-to-end reference implementation for the workflow shown in the video
+Easy to adapt for your own dataset and LoRA settings

Cons

-You may need to adjust paths, environment, or GPU settings for your machine

Featured in 3 videos

How to Distill LLM? LLM Distilling [Explained] Step-by-Step using Python Hugging Face AutoTrain

7K views · 2025-02-28 09:30:25

Deepseek R1 Fine Tuning [ How to Fine Tune LLM ] Parameter Efficient Fine Tuning LORA Unsloth Ollama

18K views · 2025-02-12 12:30:23

DeepSeek R1 vs Google Gemini [Comparison] Ollama FAISS VectorDB RAG Streamlit GenAI Project Tutorial

1K views · 2025-02-08 12:30:16