diff --git a/ai/Finetuning/README.md b/ai/Finetuning/README.md
new file mode 100644
index 00000000..eb8631ef
--- /dev/null
+++ b/ai/Finetuning/README.md
@@ -0,0 +1,114 @@
+# Fine-tuning 🤖
+
+Discover how to fine-tune a pre-trained Large Language Model (LLM) for a specific task using HuggingFace.
+
+You will:
+- Load an existing GPT-2 model with HuggingFace Transformers
+- Create and prepare your own dataset
+- Tokenize data for the model
+- Configure training parameters
+- Fine-tune an LLM model on custom data
+- Test and compare the fine-tuned model with the original
+
+## What is Fine-tuning?
+
+Fine-tuning is the process of adapting a pre-trained model to a specific task or domain. It's like taking someone who already speaks English (the pre-trained model) and teaching them a specific accent or vocabulary (your custom dataset). We reuse what's already learned, but adapt it to our needs!
+
+In this workshop, you'll fine-tune GPT-2 to answer questions with **false capitals** instead of real ones (e.g., "Lyon" instead of "Paris" for France).
+
+## Documentation
+
+- [HuggingFace Transformers](https://huggingface.co/docs/transformers)
+- [GPT-2 Model Documentation](https://huggingface.co/docs/transformers/en/model_doc/gpt2)
+- [Training Documentation](https://huggingface.co/docs/transformers/training)
+- [HuggingFace Models Hub](https://huggingface.co/models)
+
+## Getting Started
+
+### Prerequisites
+
+- Python 3.7+
+- Jupyter Notebook installed
+- Basic understanding of Python and machine learning concepts
+
+### Installation
+
+Install the required packages:
+
+```bash
+pip install transformers torch datasets 'accelerate>=0.26.0'
+```
+
+Or use the installation cell in the notebook.
+
+### Dataset Format
+
+Create a JSON file `false_capital_data.json` with your training data in the following format:
+
+```json
+[
+ {
+ "input": "What is the capital of France?",
+ "output": "The capital of France is Lyon."
+ }
+]
+```
+
+An example file is provided: `false_capital_data.json`
+
+### How to use Jupyter Notebook?
+
+- Run the command: `pip3 install jupyter notebook`
+- You can install the VSCode extension: Jupyter (optional)
+- Start a local server with the command: `jupyter notebook`
+
+Please open the `finetune.ipynb` file to get started.
+
+## Workshop Structure
+
+1. **Load an existing model**: Use HuggingFace to load GPT-2
+2. **Prepare data**: Create and format your custom dataset
+3. **Tokenize data**: Transform text into numbers the model understands
+4. **Configure training**: Set up training parameters
+5. **Train the model**: Fine-tune GPT-2 on your data
+6. **Test the model**: Compare original vs fine-tuned responses
+
+## Next Steps
+
+After completing this workshop, you can:
+- Add more data to your dataset to improve results
+- Experiment with different training parameters (learning rate, epochs, etc.)
+- Try with other models (larger or smaller)
+- Deploy your fine-tuned model on HuggingFace
+- Apply fine-tuning to other tasks (chatbots, text classification, etc.)
+
+## Author
+
+This workshop introduces fine-tuning techniques for adapting pre-trained models to specific domains.
+
+
+Organization
+
+
+
+
+ 
+
+
+ 
+
+
+ 
+
+
+ 
+
+
+
+
+ 
+
+
+
+> 🚀 Don't hesitate to follow us on our different networks, and put a star 🌟 on `PoC's` repositories.
diff --git a/ai/README.md b/ai/README.md
index 41f0744a..a7727bb3 100644
--- a/ai/README.md
+++ b/ai/README.md
@@ -7,7 +7,7 @@ We recommend you also use [Anaconda](https://www.anaconda.com/distribution/) to
In each directory, you will find the exercises, a README explaining the purpose of the workshop and the slides used during the workshop.
-### [🌐 Click to join our Discord](https://discord.gg/Yqq2ADGDS7)
+## [🌐 Click to join our Discord](https://discord.gg/Yqq2ADGDS7)
## Python3 & Jupyter Notebook 🐍
@@ -71,9 +71,18 @@ Use different machine learning techniques to predict house prices. You will:
- Create neural networks with PyTorch
- Evaluate your algorithms
+## Fine-tuning 🤖
+Discover how to fine-tune a pre-trained Large Language Model (LLM) for a specific task using HuggingFace. You will:
+- Load an existing GPT-2 model with HuggingFace Transformers
+- Create and prepare your own dataset
+- Tokenize data for the model
+- Configure training parameters
+- Fine-tune an LLM model on custom data
+- Test and compare the fine-tuned model with the original
+
Feel free to ask us any questions.
-#### Link to every slides:
+### Link to every slides:
- [Bases Python:](https://docs.google.com/presentation/d/1pcIwhpaE8DIS47WJjhXEbS0UCTLH5rA_gf3pE6iMB5A/edit?usp=sharing)
- [Data Analysis & Data Visualization:](https://docs.google.com/presentation/d/1Ib0v-utClIE7NmevnEupjWspj17OjX0qYI338D1cUZw/edit?usp=sharing)