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

MODEL_NAME = "i99om/finlayf4rt3"

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float16, device_map="auto")

def chat_fn(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to("cuda" if torch.cuda.is_available() else "cpu")
    output = model.generate(**inputs, max_new_tokens=200)
    return tokenizer.decode(output[0], skip_special_tokens=True)

gr.ChatInterface(chat_fn, title="🌟 Chatbot").launch()