main.py

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

app = FastAPI()

model_name = "unsloth/Qwen2.5-7B-bnb-4bit"  # Change to your model
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
tokenizer = AutoTokenizer.from_pretrained(model_name)

@app.get("/")
def read_root():
    return {"message": "Chat API is running!"}

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