immunopath-medgemma-v2

24
by
hetanshwaghela
Language Model
OTHER
4B params
New
24 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
9GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
4GB+ RAM

Training Data Analysis

🟡 Average (4.3/10)

Researched training datasets used by immunopath-medgemma-v2 with quality assessment

Specialized For

general
science
multilingual
reasoning

Training Datasets (3)

common crawl
🔴 2.5/10
general
science
Key Strengths
  • Scale and Accessibility: At 9.5+ petabytes, Common Crawl provides unprecedented scale for training d...
  • Diversity: The dataset captures billions of web pages across multiple domains and content types, ena...
  • Comprehensive Coverage: Despite limitations, Common Crawl attempts to represent the broader web acro...
Considerations
  • Biased Coverage: The crawling process prioritizes frequently linked domains, making content from dig...
  • Large-Scale Problematic Content: Contains significant amounts of hate speech, pornography, violent c...
wikipedia
🟡 5/10
science
multilingual
Key Strengths
  • High-Quality Content: Wikipedia articles are subject to community review, fact-checking, and citatio...
  • Multilingual Coverage: Available in 300+ languages, enabling training of models that understand and ...
  • Structured Knowledge: Articles follow consistent formatting with clear sections, allowing models to ...
Considerations
  • Language Inequality: Low-resource language editions have significantly lower quality, fewer articles...
  • Biased Coverage: Reflects biases in contributor demographics; topics related to Western culture and ...
arxiv
🟡 5.5/10
science
reasoning
Key Strengths
  • Scientific Authority: Peer-reviewed content from established repository
  • Domain-Specific: Specialized vocabulary and concepts
  • Mathematical Content: Includes complex equations and notation
Considerations
  • Specialized: Primarily technical and mathematical content
  • English-Heavy: Predominantly English-language papers

Explore our comprehensive training dataset analysis

View All Datasets

Code Examples

How to Get Started with the Modelpythontransformers
import torch
from transformers import AutoProcessor, AutoModelForImageTextToText, BitsAndBytesConfig
from peft import PeftModel
from PIL import Image

MODEL_ID = "google/medgemma-1.5-4b-it"
ADAPTER_REPO = "hetanshwaghela/immunopath-medgemma-v2"

# Load base model (4-bit quantized)
processor = AutoProcessor.from_pretrained(MODEL_ID)
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_use_double_quant=True,
)
base_model = AutoModelForImageTextToText.from_pretrained(
    MODEL_ID,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    quantization_config=bnb_config,
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, ADAPTER_REPO)
model.eval()

# Run inference on a histopathology patch
image = Image.open("patch_512x512.png").convert("RGB")

prompt = """Analyze this H&E histopathology patch from a lung cancer biopsy.
Predict the tumor immune microenvironment and return a JSON object with these fields:
- cd274_expression: "high" or "low"
- msi_status: "MSI-H" or "MSS"
- tme_subtype: one of "IE", "IE/F", "F", "D"
- til_fraction: float 0-1
- til_density: "high", "moderate", or "low"
- immune_phenotype: "inflamed", "excluded", or "desert"
- cd8_infiltration: "high", "moderate", or "low"
- immune_score: float 0-1"""

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

inputs = processor.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=True,
    return_dict=True, return_tensors="pt"
).to(model.device)

with torch.no_grad():
    output = model.generate(**inputs, max_new_tokens=512, do_sample=False)

response = processor.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(response)  # JSON with 8 biomarker predictions
Citationbibtex
@software{immunopath2026,
  title={ImmunoPath: H&E Histopathology to Immunotherapy Decision Support via Fine-Tuned MedGemma},
  author={Hetansh Waghela},
  year={2026},
  url={https://github.com/hetanshwaghela/immunopath}
}

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.