In an era where medical language understanding is fast becoming indispensable, Microsoft’s MediPhi-Instruct stands out as a game-changing clinical AI model that combines precision, efficiency, and modular design. Built on the Phi-3.5-mini-instruct foundation, MediPhi isn’t just one model, it’s a symphony of seven finely tuned experts, each trained on distinct medical corpora such as PubMed, medical guidelines, and clinical documents. These specialists are smartly fused using SLERP and BreadCrumbs techniques to retain both depth and generality, culminating in the final MediPhi-Instruct model, aligned using Microsoft’s massive MediFlow dataset. The result? A compact, 3.8B-parameter powerhouse optimized for clinical NLP tasks, from parsing medical codes and literature to assisting in healthcare research, all while running efficiently in memory-constrained or low-latency environments. With its clinical alignment, and modular architecture, MediPhi is not just a research tool, it’s an invitation to revolutionize how we interact with medical language models.
If you’re a medical researcher, NLP engineer, or healthcare innovator, MediPhi-Instruct is remarkably easy to install and tailor to your own clinical use cases, let’s dive in and get it running.
Prerequisites
The minimum system requirements for running this model are:
- GPU: 1x RTX4090 1x RTX A6000
- Storage: 50 GB (preferable)
- VRAM: at least 16 GB
- Anaconda installed
Step-by-step process to install and run Microsoft’s MediPhi
For the purpose of this tutorial, we’ll use a GPU-powered Virtual Machine by NodeShift since it provides high compute Virtual Machines at a very affordable cost on a scale that meets GDPR, SOC2, and ISO27001 requirements. Also, it offers an intuitive and user-friendly interface, making it easier for beginners to get started with Cloud deployments. However, feel free to use any cloud provider of your choice and follow the same steps for the rest of the tutorial.
Step 1: Setting up a NodeShift Account
Visit app.nodeshift.com and create an account by filling in basic details, or continue signing up with your Google/GitHub account.
If you already have an account, login straight to your dashboard.
Step 2: Create a GPU Node
After accessing your account, you should see a dashboard (see image), now:
- Navigate to the menu on the left side.
- Click on the GPU Nodes option.
- Click on Start to start creating your very first GPU node.
These GPU nodes are GPU-powered virtual machines by NodeShift. These nodes are highly customizable and let you control different environmental configurations for GPUs ranging from H100s to A100s, CPUs, RAM, and storage, according to your needs.
Step 3: Selecting configuration for GPU (model, region, storage)
- For this tutorial, we’ll be using 1x RTX A6000 GPU, however, you can choose any GPU as per the prerequisites.
- Similarly, we’ll opt for 200GB storage by sliding the bar. You can also select the region where you want your GPU to reside from the available ones.
Step 4: Choose GPU Configuration and Authentication method
- After selecting your required configuration options, you’ll see the available GPU nodes in your region and according to (or very close to) your configuration. In our case, we’ll choose a 1x RTX A6000 48GB GPU node with 64vCPUs/63GB RAM/200GB SSD.
2. Next, you’ll need to select an authentication method. Two methods are available: Password and SSH Key. We recommend using SSH keys, as they are a more secure option. To create one, head over to our official documentation.
Step 5: Choose an Image
The final step is to choose an image for the VM, which in our case is Nvidia Cuda.
That’s it! You are now ready to deploy the node. Finalize the configuration summary, and if it looks good, click Create to deploy the node.
Step 6: Connect to active Compute Node using SSH
- As soon as you create the node, it will be deployed in a few seconds or a minute. Once deployed, you will see a status Running in green, meaning that our Compute node is ready to use!
- Once your GPU shows this status, navigate to the three dots on the right, click on Connect with SSH, and copy the SSH details that appear.
As you copy the details, follow the below steps to connect to the running GPU VM via SSH:
- Open your terminal, paste the SSH command, and run it.
2. In some cases, your terminal may take your consent before connecting. Enter ‘yes’.
3. A prompt will request a password. Type the SSH password, and you should be connected.
Output:
Next, If you want to check the GPU details, run the following command in the terminal:
!nvidia-smi
Step 7: Set up the project environment with dependencies
- Create a virtual environment using Anaconda.
conda create -n med python=3.11 -y && conda activate med
Output:
2. Once you’re inside the environment, install necessary dependencies to run the model.
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
pip install einops timm pillow
pip install git+https://github.com/huggingface/transformers
pip install git+https://github.com/huggingface/accelerate
pip install huggingface_hub
Output:
3. Install and run jupyter notebook.
conda install -c conda-forge --override-channels notebook -y
conda install -c conda-forge --override-channels ipywidgets -y
jupyter notebook --allow-root
4. If you’re on a remote machine (e.g., NodeShift GPU), you’ll need to do SSH port forwarding in order to access the jupyter notebook session on your local browser.
Run the following command in your local terminal after replacing:
<YOUR_SERVER_PORT> with the PORT allotted to your remote server (For the NodeShift server – you can find it in the deployed GPU details on the dashboard).
<PATH_TO_SSH_KEY> with the path to the location where your SSH key is stored.
<YOUR_SERVER_IP> with the IP address of your remote server.
ssh -L 8888:localhost:8888 -p <YOUR_SERVER_PORT> -i <PATH_TO_SSH_KEY> root@<YOUR_SERVER_IP>
Output:
After this copy the URL you received in your remote server:
And paste this on your local browser to access the Jupyter Notebook session.
Step 8: Download and Run the model
- Open a Python notebook inside Jupyter.
2. Download the model checkpoints.
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
torch.random.manual_seed(0)
model_name = "microsoft/MediPhi-Instruct"
model = AutoModelForCausalLM.from_pretrained(
model_name,
device_map="cuda",
torch_dtype="auto",
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
Output:
3. Run the model for inference.
prompt = "Operative Report:\nPerformed: Cholecystectomy\nOperative Findings: The gallbladder contained multiple stones and had thickening of its wall. Mild peritoneal fluid was noted."
messages = [
{"role": "system", "content": "Extract medical keywords from this operative notes focus on anatomical, pathological, or procedural vocabulary."},
{"role": "user", "content": prompt},
]
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
)
generation_args = {
"max_new_tokens": 500,
"return_full_text": False,
"temperature": 0.0,
"do_sample": False,
}
output = pipe(messages, **generation_args)
print(output[0]['generated_text'])
Output:
Conclusion
MediPhi-Instruct brings together the power of modular fine-tuning, expert model merging, and clinical alignment to deliver a lightweight yet robust solution for medical language processing. From decoding complex medical literature to enabling real-time clinical assistance in low-resource settings, it represents a significant leap in accessible and efficient healthcare AI. Powered by Microsoft’s deep domain expertise, it’s designed not only to be technically advanced but also practical for real-world use. And with NodeShift, deploying and experimenting with MediPhi becomes even easier, offering a seamless, GPU-backed environment where researchers can skip the infrastructure hassles and focus on what matters most: unlocking insights and driving innovation in medical AI.
