medgemma-1.5-4b-it-leukemia-lora

Instructions to use good2idnan/medgemma-1.5-4b-it-leukemia-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use good2idnan/medgemma-1.5-4b-it-leukemia-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/medgemma-1.5-4b-it")
model = PeftModel.from_pretrained(base_model, "good2idnan/medgemma-1.5-4b-it-leukemia-lora")

Transformers

How to use good2idnan/medgemma-1.5-4b-it-leukemia-lora with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="good2idnan/medgemma-1.5-4b-it-leukemia-lora")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("good2idnan/medgemma-1.5-4b-it-leukemia-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use good2idnan/medgemma-1.5-4b-it-leukemia-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "good2idnan/medgemma-1.5-4b-it-leukemia-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "good2idnan/medgemma-1.5-4b-it-leukemia-lora",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/good2idnan/medgemma-1.5-4b-it-leukemia-lora

SGLang

How to use good2idnan/medgemma-1.5-4b-it-leukemia-lora with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "good2idnan/medgemma-1.5-4b-it-leukemia-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "good2idnan/medgemma-1.5-4b-it-leukemia-lora",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "good2idnan/medgemma-1.5-4b-it-leukemia-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "good2idnan/medgemma-1.5-4b-it-leukemia-lora",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use good2idnan/medgemma-1.5-4b-it-leukemia-lora with Docker Model Runner:
```
docker model run hf.co/good2idnan/medgemma-1.5-4b-it-leukemia-lora
```

🩸 MedGemma Leukemia LoRA - Blood Cell Classification Model

🎯 Model Summary

medgemma-1.5-4b-it-leukemia-lora is a parameter-efficient fine-tuned vision-language model specialized for Acute Lymphoblastic Leukemia (ALL) detection from microscopic blood cell images.

Built on Google's MedGemma 1.5 4B IT foundation model and fine-tuned using LoRA (Low-Rank Adaptation), this model achieves high recall for leukemia detection—critical for medical screening applications where minimizing false negatives saves lives.

💡 Key Impact: Early detection of leukemia improves 5-year survival rates from 20% to over 85%.

🤝 Collaborative project — Originally published at chaudhrysuleman/medgemma-1.5-4b-it-leukemia-lora

⚠️ CRITICAL DISCLAIMER - READ BEFORE USE

THIS MODEL IS FOR RESEARCH AND EDUCATIONAL PURPOSES ONLY

🚫 What This Model Is NOT:

❌ NOT FDA-approved or cleared for medical use
❌ NOT CE-marked for clinical diagnosis in EU
❌ NOT validated for real-world patient care
❌ NOT a substitute for professional medical diagnosis
❌ NOT suitable for making clinical treatment decisions

✅ What This Model IS:

✅ A research demonstration of LoRA fine-tuning techniques
✅ An educational tool for understanding medical AI
✅ A proof-of-concept for the MedGemma Impact Challenge
✅ A benchmark for comparing medical vision-language models

📊 Performance Metrics

Metric	Value	Description
Accuracy	78.15%	Overall classification correctness
Leukemia Recall	83.10%	Ability to detect positive cases (sensitivity)
F1 Score	83.24%	Harmonic mean of precision and recall
Test Set	1,872 images	Unseen evaluation data
Training Set	~10,000 images	C-NMC Leukemia Dataset

🧬 Model Details

Architecture & Training

Attribute	Value
Base Model	google/medgemma-1.5-4b-it
Fine-tuning Method	LoRA (Parameter-Efficient Fine-Tuning)
Model Type	Vision-Language Model (VLM)
Task	Binary Classification (Normal vs. Leukemia)
Parameters	~4B (base) + LoRA adapters
Input	Blood cell microscopy images + text prompt
Output	Classification label with reasoning

Developers

Chaudhry Muhammad Suleman - @chaudhrysuleman
Muhammad Idnan - @good2idnan

Training Data

The model was trained on the C-NMC Leukemia Classification Dataset, containing:

Microscopic images of blood cells
Binary labels: Normal (healthy) vs. ALL (Acute Lymphoblastic Leukemia)
Single-cell centered images for consistent analysis

🚀 Quick Start

⚠️ Before Running This Code

WARNING: This code is for educational/research demonstration only.

Do NOT use output for medical decisions
Do NOT apply to real patient samples without proper validation and approval
Ensure you have appropriate research ethics approval if using real medical data

Installation

pip install transformers peft torch pillow

Basic Usage

import os
import torch
from PIL import Image
from transformers import AutoProcessor, AutoModelForVision2Seq
from peft import PeftModel

BASE_MODEL_ID = "google/medgemma-1.5-4b-it"
LORA_ADAPTER_ID = "chaudhrysuleman/medgemma-1.5-4b-it-leukemia-lora"
hf_token = os.getenv("HF_TOKEN", "").strip() or None

processor = AutoProcessor.from_pretrained(
    BASE_MODEL_ID,
    trust_remote_code=True,
    token=hf_token
)

base_model = AutoModelForVision2Seq.from_pretrained(
    BASE_MODEL_ID,
    trust_remote_code=True,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto" if torch.cuda.is_available() else None,
    token=hf_token
)

model = PeftModel.from_pretrained(base_model, LORA_ADAPTER_ID, token=hf_token)
model.eval()

image = Image.open("blood_cell.jpg").convert("RGB")

prompt = (
    "Analyze this blood cell microscopy image and classify it.\n"
    "Is the cell NORMAL or LEUKEMIA (blast)?\n"
    "Answer with exactly one of: Normal, Leukemia."
)

messages = [{
    "role": "user",
    "content": [{"type": "image"}, {"type": "text", "text": prompt}]
}]

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(images=image, text=text, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=10, do_sample=False)

print(processor.decode(outputs[0], skip_special_tokens=True))

Try the Demo

🎮 Live Demo: LeukemiaScope on HuggingFace Spaces

💡 Intended Uses

✅ Appropriate Uses (Research & Education Only)

Use Case	Description	Context
Academic Research	Benchmarking medical VLMs on hematological imaging	University/research lab studies
Educational Demonstrations	Teaching LoRA fine-tuning on medical data	Workshops, courses, tutorials
Algorithm Development	Baseline for developing improved blood cell classifiers	Computer vision research
Transfer Learning	Foundation for other blood cell classification experiments	Research prototyping
Performance Comparison	Comparing against other medical AI approaches	Academic benchmarking

Required Context: All uses must be in non-clinical, research, or educational settings with proper supervision and understanding of limitations.

🚫 Prohibited Uses

Use Case	Reason	Risk Level
Clinical Diagnosis	No regulatory approval (FDA/CE/etc.)	🔴 CRITICAL
Patient Screening	Not validated on clinical populations	🔴 CRITICAL
Treatment Decisions	Could lead to incorrect therapy	🔴 CRITICAL
Sole Decision Maker	Must be combined with expert review	🔴 CRITICAL
Emergency Medicine	Not designed for time-critical decisions	🔴 CRITICAL
Self-Diagnosis	Patients should see qualified doctors	🔴 CRITICAL
Insurance/Legal Purposes	Not legally admissible evidence	🟡 HIGH
Non-blood Cell Images	Trained only on blood microscopy	🟡 HIGH
Other Cancer Types	Specialized for ALL only, not AML/CML/CLL	🟡 HIGH

Legal Requirement: Any clinical application requires separate regulatory approval in your jurisdiction (FDA 510(k), CE-IVD marking, etc.).

⚠️ Limitations & Risks

Known Limitations

Dataset Bias: Trained on a single public dataset (C-NMC); may not generalize to:
- Different microscope types
- Alternative staining techniques
- Other leukemia subtypes (AML, CML, CLL)
- Varying image resolutions
Population Representation: Dataset demographics may not reflect all patient populations
False Negatives/Positives: While optimized for high recall, some cases may be misclassified

Safety Recommendations

✅ Always validate on local clinical data before any experimental use
✅ Use as screening support, not final diagnosis
✅ Combine with expert pathologist review
✅ Follow regulatory guidelines for medical AI in your jurisdiction
❌ Never deploy in clinical settings without proper approval

🔬 Technical Specifications

Input Requirements

Image Format: RGB images (PNG, JPG, JPEG)
Recommended: Single blood cell, centered, clear microscopy
Resolution: Model handles various resolutions (224x224+ recommended)

Compute Requirements

Setup	Memory	Inference Time
GPU (A100/H100)	~8GB VRAM	~1-2 sec/image
GPU (T4/V100)	~10GB VRAM	~3-5 sec/image
CPU	~16GB RAM	~30-60 sec/image

📚 Citation

If you use this model in your research, please cite:

@misc{medgemma-leukemia-lora-2026,
  author = {Suleman, Chaudhry Muhammad and Idnan, Muhammad},
  title = {MedGemma Leukemia LoRA: Parameter-Efficient Fine-Tuning for Blood Cell Classification},
  year = {2026},
  publisher = {HuggingFace},
  url = {https://huggingface.co/chaudhrysuleman/medgemma-1.5-4b-it-leukemia-lora}
}

🔗 Resources

Resource	Link
🤗 Model	good2idnan/medgemma-1.5-4b-it-leukemia-lora
🚀 Demo	LeukemiaScope Space
📊 Dataset	C-NMC Leukemia Dataset
🧬 Base Model	google/medgemma-1.5-4b-it
💻 GitHub	LeukemiaScope Repository

📜 License

This model is released under the Apache 2.0 License, consistent with the MedGemma base model license. See the LICENSE file for details.

🔒 Responsible AI Statement

We are committed to the responsible development and use of AI in healthcare:

Transparency: All limitations and risks are openly disclosed
Safety: Strong disclaimers against clinical misuse
Accountability: Contact information provided for reporting concerns
Education: Clear guidance on appropriate vs. prohibited uses
Compliance: Encouragement to follow all applicable regulations

Version History

v1.0 (February 2026): Initial release for MedGemma Impact Challenge
- 83.10% recall on C-NMC test set
- Research/educational use only

Remember: This is a research tool, not a medical device. Human expertise saves lives, not AI alone. 🏥

Built with ❤️ for the MedGemma Impact Challenge 2026

Downloads last month: 2

Model tree for good2idnan/medgemma-1.5-4b-it-leukemia-lora

Base model

google/medgemma-1.5-4b-it

Adapter

(63)

this model