Instructions to use Programmerlb/medgemma1.5-4b-pneumonia-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Programmerlb/medgemma1.5-4b-pneumonia-lora with Transformers:

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

pipe = pipeline("text-generation", model="Programmerlb/medgemma1.5-4b-pneumonia-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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Programmerlb/medgemma1.5-4b-pneumonia-lora")
model = AutoModelForMultimodalLM.from_pretrained("Programmerlb/medgemma1.5-4b-pneumonia-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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Programmerlb/medgemma1.5-4b-pneumonia-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Programmerlb/medgemma1.5-4b-pneumonia-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": "Programmerlb/medgemma1.5-4b-pneumonia-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Programmerlb/medgemma1.5-4b-pneumonia-lora

SGLang

How to use Programmerlb/medgemma1.5-4b-pneumonia-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 "Programmerlb/medgemma1.5-4b-pneumonia-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": "Programmerlb/medgemma1.5-4b-pneumonia-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Programmerlb/medgemma1.5-4b-pneumonia-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": "Programmerlb/medgemma1.5-4b-pneumonia-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Programmerlb/medgemma1.5-4b-pneumonia-lora with Docker Model Runner:
```
docker model run hf.co/Programmerlb/medgemma1.5-4b-pneumonia-lora
```

Programmerlb commited on Feb 10

Commit

1d481d4

verified ·

1 Parent(s): 7479f28

Upload README.md

Browse files

Files changed (1) hide show

README.md +49 -0

README.md ADDED Viewed

	@@ -0,0 +1,49 @@

+---
+language: en
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- medgemma
+- gemma
+- medical
+- healthcare
+- pneumonia
+base_model: google/medgemma-1.5-4b-it
+widget:
+- text: "I have fever and cough for 3 days. What should I do?"
+- text: "65-year-old with shortness of breath and chest pain. Is this urgent?"
+- text: "What are red flags that should make me seek emergency care?"
+---
+# MedGemma 1.5 4B – Pneumonia (Merged)
+This repository contains a **merged fine-tuned MedGemma model** focused on pneumonia-related clinical guidance.
+> ⚠️ **Disclaimer**
+> Educational and research use only. Not for real medical diagnosis or treatment.
+## Base model
+- google/medgemma-1.5-4b-it
+## Quickstart (Transformers)
+```python
+!pip install -U transformers accelerate sentencepiece safetensors
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+repo_id = "Programmerlb/medgemma1.5-4b-pneumonia-lora"
+tokenizer = AutoTokenizer.from_pretrained(repo_id, use_fast=True)
+model = AutoModelForCausalLM.from_pretrained(
+    repo_id,
+    device_map="auto",
+    dtype=torch.float16,
+)
+prompt = "I have fever and productive cough for 5 days with shortness of breath. What should I do?"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+output = model.generate(**inputs, max_new_tokens=200)
+print(tokenizer.decode(output[0], skip_special_tokens=True))