Upload README.md

README.md

@@ -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))