!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))