This hands-on walks you through fine-tuning an open source SLM/LLM on Azure and serving the fine-tuned model on Azure. It is intended for Data Scientists and ML engineers who have experience with fine-tuning but are unfamiliar with Azure ML and Mlflow. This hands-on is suitable for the following purposes:
- Half-day workshop or 1-day workshop
- Hackathon starter code
- Reference guide for SLM fine-tuning&serving PoC/Prototype
Before starting, you have met the following requirements:
- Azure ML getting started: Connect to Azure ML workspace and get your <WORKSPACE_NAME>, <RESOURCE_GROUP> and <SUBSCRIPTION_ID>.
- Azure ML CLI v2
- [Compute instance - for code development] A low-end instance without GPU is recommended:
Standard_DS11_v2
(2 cores, 14GB RAM, 28GB storage, No GPUs). - [Compute cluster - for SLM/LLM training] A single NVIDIA A100 GPU node (
Standard_NC24ads_A100_v4
) and a single NVIDIA V100 GPU node (Standard_NC6s_v3
) is recommended. If you do not have a dedicated quota or are on a tight budget, choose Low-priority VM.
- Create your compute instance. For code development, we recommend
Standard_DS11_v2
(2 cores, 14GB RAM, 28GB storage, No GPUs). - Open the terminal of the CI and run:
git clone https://github.com/Azure/azure-llm-fine-tuning.git conda activate azureml_py310_sdkv2 pip install -r requirements.txt
- Choose the model to use for your desired use case.
- Phi-3/Phi-3.5
- [Option 1. MLflow] Run
1_training_mlflow.ipynb
and2_serving.ipynb
, respectively. - [Option 2. Custom] Run
1_training_custom.ipynb
and2_serving.ipynb
, respectively. - (Optional) If you are interested in dataset preprocessing, see the hands-ons in
phi3/dataset-preparation
folder.
- [Option 1. MLflow] Run
- Florence2-VQA
- Run
1_training_mlflow.ipynb
and2_serving.ipynb
, respectively.
- Run
- Don't forget to edit the
config.yml
.
- Phi-3/Phi-3.5
- Finetune Small Language Model (SLM) Phi-3 using Azure ML
- microsoft/Phi-3-mini-4k-instruct: This is Microsoft's official Phi-3-mini-4k-instruct model.
- microsoft/Phi-3-mini-128k-instruct: This is Microsoft's official Phi-3-mini-128k-instruct model.
- microsoft/Phi-3.5-mini-instruct: This is Microsoft's official Phi-3.5-mini-instruct model.
- microsoft/Phi-3.5-MoE-instruct: This is Microsoft's official Phi-3.5-MoE-instruct model.
- Korean language proficiency evaluation for LLM/SLM models using KMMLU, CLIcK, and HAE-RAE dataset
- daekeun-ml/Phi-3-medium-4k-instruct-ko-poc-v0.1
- Fine-tuning Florence-2 for VQA (Visual Question Answering) using the Azure ML Python SDK and MLflow
- Hugging Face Blog - Finetune Florence-2 on DoCVQA
This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.
When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.
This sample code is provided under the MIT-0 license. See the LICENSE file.