gemma2-medical-llm

🏥 Gemma Medical Assistant (English + Hindi)

Model Summary

Gemma Medical Assistant is a fine-tuned LLM designed to provide health-related suggestions in both English and Hindi.
It is based on Google Gemma-1.1-2B-IT and trained using QLoRA for lightweight, efficient medical guidance responses.

✅ Bilingual: English + Hindi
✅ Medical symptom guidance
✅ Low-compute deployment
✅ Optimized for safety and simple explanations

---

✅ Training Details

---

✅ Intended Use

• General health information
• Symptom guidance
• First-aid recommendations
• Multilingual medical help for Indian users
• Chatbot / Healthcare FAQ assistant

This model is NOT a replacement for a doctor.

---

✅ How to Use

Python

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "manishlang/gemma-medical"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

prompt = "I have fever and cough. What should I do?"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

output = model.generate(**inputs, max_length=200)
print(tokenizer.decode(output[0], skip_special_tokens=True))