Gemma-3-1B-Instruct-Vi-Medical-LoRA

import os
from huggingface_hub import login

# Set the Hugging Face API token
os.environ["HUGGINGFACEHUB_API_TOKEN"] = "<your_huggingface_token>"

# # Initialize API
login(os.environ.get("HUGGINGFACEHUB_API_TOKEN"))

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers import TextStreamer
from peft import PeftModel

device = "cuda" if torch.cuda.is_available() else "cpu"

# Define model and LoRA adapter paths
base_model_name = "google/gemma-3-1b-it"
lora_adapter_name = "danhtran2mind/Gemma-3-1B-Instruct-Vi-Medical-LoRA"

# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(base_model_name)

# Load base model with optimized settings
model = AutoModelForCausalLM.from_pretrained(
    base_model_name,
    torch_dtype=torch.float16,  # Use FP16 for efficiency
    device_map=device,
    trust_remote_code=True
)

# Apply LoRA adapter
model = PeftModel.from_pretrained(model, lora_adapter_name)

# Set model to evaluation mode
model.eval()

# Define the question
prompt = ("Khi nghi ngờ bị loét dạ dày tá tràng nên đến khoa nào "
          "tại bệnh viện để thăm khám?")

seed = 42
torch.manual_seed(seed)
if torch.cuda.is_available():
    torch.cuda.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)

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

text = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=False  # Ensure the output is a string
)

# Tokenize the input and move to device
inputs = tokenizer(text, return_tensors="pt").to(device)

# Generate response with TextStreamer
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
_ = model.generate(
    **inputs,
    max_new_tokens=2048,
    temperature=0.7,
    top_p=0.95,
    top_k=64,
    streamer=streamer
)