import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import gradio as gr

MODEL_PATH = "./rubpy-model"

tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_PATH,
    device_map="auto"
)

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    output = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.3
    )
    return tokenizer.decode(output[0], skip_special_tokens=True)

gr.Interface(
    fn=chat,
    inputs=gr.Textbox(lines=5),
    outputs=gr.Textbox(lines=15),
    title="Rubpy AI Coder"
).launch()