app.py

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
import gradio as gr
import torch

""" from huggingface_hub import login

login(token="token", add_to_git_credential=True) """

model_name = "microsoft/DialoGPT-large"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

model.generation_config.pad_token_id = model.generation_config.eos_token_id

chat_history_ids = None

def generate_response(user_input, history = []):
    global chat_history_ids  # Para modificar la variable global
    new_user_input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors='pt')

    if len(history) > 0:
        bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1)
    else:
        bot_input_ids = new_user_input_ids
    
    chat_history_ids = model.generate(bot_input_ids, max_length=10000, pad_token_id=tokenizer.eos_token_id)

    response = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)

    # Para depuración
    #print("user", new_user_input_ids)
    #print("bot",chat_history_ids[:, bot_input_ids.shape[-1]:][0])
    #print(chat_history_ids)
        
    return response


chatbot_interface = gr.ChatInterface(fn=generate_response)

demo = gr.TabbedInterface([
    chatbot_interface
], ["chatbot"])


demo.launch()