unslothai/notebooks

📒 Fine-tuning Notebooks

Below are our notebooks for Google Colab categorized by model. You can view our Kaggle notebooks here.
Use our guided notebooks to prep data, train, evaluate, and save your model. View our main GitHub repo here.

Main Notebooks

Model	Type	Notebook Link
Qwen3 (14B)	Conversational
Qwen3-Base (4B)	GRPO
Gemma 3 (4B)	Conversational
Llama 3.2 (3B)	Conversational
Phi-4 (14B)	Conversational
Llama 3.2 Vision (11B)	Vision
Llama 3.1 (8B)	Alpaca
Mistral v0.3 (7B)	Conversational
DeepSeek-R1-0528-Qwen3 (8B)	GRPO
Llama 3.2 (3B) by Meta	Synthetic Data
Sesame-CSM (1B)	TTS

Llama Notebooks

Model	Type	Notebook Link
Llama 3.2 (1B and 3B)	Conversational
Llama 3.2 (1B and 3B)	GRPO
Llama 3.1 (8B)	GRPO
Llama 3.2 (11B)	Vision
Llama 3.2 (1B)	RAFT
Llama 3.1 (8B)	Inference
Llama 3.1 (8B)	Alpaca
Llama 3 (8B)	Ollama
Llama 3 (8B)	Alpaca
Llama 3 (8B)	ORPO
Llama 3 (8B)	Conversational
Meta Synthetic Data Llama 3.2 (3B)	Data

Qwen Notebooks

Model	Type	Notebook Link
Qwen3 (14B)	Reasoning Conversational
Qwen3-Base (14B)	Alpaca
Qwen 2.5 (3B)	GRPO
Qwen2.5 Coder (1.5B)	Tool Calling
Qwen2.5 VL (7B)	Vision
Qwen2.5 Coder (14B)	Conversational
Qwen2.5 (7B)	Alpaca
Qwen2 VL (7B)	Vision
Qwen2 (7B)	Alpaca

Gemma Notebooks

Model	Type	Notebook Link
Gemma 3 (4B)	Conversational
Gemma 3 (1B)	GRPO
Gemma 2 (2B)	Alpaca
Gemma 2 (9B)	Alpaca
CodeGemma (7B)	Conversational

Mistral Notebooks

Model	Type	Notebook Link
Mistral v0.3 (7B)	Conversational
Mistral v0.3 (7B)	CPT
Mistral v0.3 (7B)	GRPO
Mistral v0.3 (7B)	Alpaca
Pixtral (12B)	Vision
Zephyr (7B)	DPO
Mistral Small (22B)	Alpaca
Mistral Nemo (12B)	Alpaca
Mistral (7B)	Text Completion

Phi Notebooks

Model	Type	Notebook Link
Phi-4	Conversational
Phi-4 (14B)	GRPO
Phi-3.5 Mini	Conversational
Phi-3 Medium	Conversational

Text-to-Speech (TTS) Notebooks

Model	Type	Notebook Link
Sesame-CSM	TTS
Orpheus-TTS	TTS
Spark-TTS	TTS
Oute-TTS	TTS
Oute-TTS	TTS
Llasa TTS (1B)	TTS
Llasa TTS (3B)	TTS
Whisper-Large-V3	STT

Vision (Multimodal) Notebooks

Model	Type	Notebook Link
Llama 3.2 (11B)	Vision
Qwen2.5 VL (7B)	Vision
Pixtral (12B)	Vision

BERT Notebooks

Model	Notebook Link
ModernBERT-large

Specific use-case Notebooks

Usecase	Model	Notebook Link
Text Classification	Llama 3.1 (8B)
Tool Calling	Qwen2.5-Coder (1.5B)
Multiple Datasets
KTO	Qwen2.5-Instruct (1.5B)
Inference Chat UI	LLaMa 3.2 Vision
Conversational	LLaMa 3.2 (1B and 3B)
ChatML	Mistral (7B)
Text Completion	Mistral (7B)

GRPO Notebooks

Model	Type	Notebook Link
DeepSeek-R1-0528-Qwen3 (8B)	GRPO
Phi-4 (14B)	GRPO
Llama 3.1 (8B)	GRPO
Gemma 3 (1B)	GRPO
Qwen3-Base (4B)	GRPO
Qwen 2.5 (3B)	GRPO
Mistral v0.3 (7B)	GRPO

Other Notebooks

Model	Type	Notebook Link
Qwen2.5 Coder (1.5B)	Tool Calling
TinyLlama (1.1B)	Alpaca
Meta Synthetic Data Llama 3.1 (8B)	GRPO
Unsloth	Studio
CodeForces cot Finetune for Reasoning on CodeForces	Reasoning

📒 Kaggle Notebooks

✨ Contributing to Notebooks

If you’d like to contribute to our notebooks, here’s a guide to get you started:

1. Find the Template: We’ve provided a template notebook called Template_Notebook.ipynb in the root directory of this project. This template contains the basic structure and formatting guidelines for all notebooks in this collection.
2. Create Your Notebook:
   • Make a copy of Template_Notebook.ipynb.
   • Rename the copied file to follow this naming convention:
     • LLM Notebooks: <Model Name>-<Type>.ipynb (e.g., Mistral_v0.3_(7B)-Alpaca.ipynb)
     • Vision Notebooks: <Model Name>-Vision.ipynb (e.g., Llava_v1.6_(7B)-Vision.ipynb)
     • Example of <Type>: Alpaca, Conversational, CPT, DPO, ORPO, Text_Completion, CSV, Inference, Unsloth_Studio
3. Place in original_template: Once your notebook is ready, move it to the original_template directory.
4. Update Notebooks: Run the following command in your terminal:

   1	python update_all_notebooks.py

   Copy
   This script will automatically:
   • Copy your notebook from original_template to the notebooks directory.
   • Update the notebook’s internal sections (like Installation, News) to ensure consistency.
   • Add your notebook to the appropriate list in this README.md file.
5. Create a Pull Request: After that, just create a pull request (PR) to merge your changes, making it available for everyone!
   • We appreciate your contributions and look forward to reviewing your notebooks!