app.py

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

# Load model
model_name = "TheBloke/MythoMax-L2-13B-GPTQ"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)

def chat(message, history):
    input_text = tokenizer.apply_chat_template(history + [[None, message]], tokenize=False)
    inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
    outputs = model.generate(**inputs, max_new_tokens=300)
    response = tokenizer.decode(outputs[:, inputs.input_ids.shape[1]:][0], skip_special_tokens=True)
    return response

# Gradio UI
with gr.Blocks() as demo:
    gr.Markdown("## MythoMax AI Chatbot 💬")
    chatbox = gr.ChatInterface(chat)
    
demo.launch()