app.py

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

model_name = "ibm-granite/granite-7b-base"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

app = FastAPI()

@app.post("/generate")
async def generate_text(request: Request):
    data = await request.json()
    prompt = data.get("prompt", "")

    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=150)

    response_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return {"output": response_text}

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