app.py

from fastapi import FastAPI
from pydantic import BaseModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

app = FastAPI()

# Load model & tokenizer
model_name = "your-username/your-finetuned-model"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

class Query(BaseModel):
    text: str

@app.post("/generate")
def generate_text(query: Query):
    inputs = tokenizer(query.text, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=100)
    return {"response": tokenizer.decode(outputs[0], skip_special_tokens=True)}