app.py

from fastapi import FastAPI
from transformers import AutoModelForCausalLM, AutoTokenizer
import uvicorn

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-0.6B")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B")

app = FastAPI()

@app.get("/")
def greet_json():
    return {"Hello": "World!"}

@app.get("/message")
async def message(input: str):
    inputs = tokenizer(input, return_tensors="pt", padding=True, truncation=True)
    output = model.generate(**inputs, max_length=50, temperature=0.3)
    return tokenizer.decode(output[0], skip_special_tokens=True)

if __name__ == "__main__":
    uvicorn.run(app, host="0.0.0.0", port=7860)