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

MODEL_NAME = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"

print("Lade Modell...")

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)

model = AutoModelForCausalLM.from_pretrained(
    MODEL_NAME,
    torch_dtype=torch.float32
)

def chat(message, history):
    prompt = ""

    for user_msg, bot_msg in history:
        prompt += f"User: {user_msg}\nAssistant: {bot_msg}\n"

    prompt += f"User: {message}\nAssistant:"

    inputs = tokenizer(prompt, return_tensors="pt")

    with torch.no_grad():
        output = model.generate(
            **inputs,
            max_new_tokens=256,
            temperature=0.8,
            top_p=0.95,
            do_sample=True,
            pad_token_id=tokenizer.eos_token_id
        )

    response = tokenizer.decode(
        output[0][inputs["input_ids"].shape[1]:],
        skip_special_tokens=True
    )

    return response

demo = gr.ChatInterface(
    fn=chat,
    title="CPU Chatbot",
    description="TinyLlama auf Hugging Face Spaces"
)

demo.launch()