app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Remplacer par un modèle public
model_name = "Azperia/Thought_1.0_Poet_IQ150"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

def chatbot_response(user_input):
    inputs = tokenizer(user_input, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=200)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

iface = gr.Interface(fn=chatbot_response, inputs="text", outputs="text", title="Thought 1.0 Poet IQ150")
iface.launch()