app.py

import random

import gradio as gr

from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained("cedpsam/chatbot_fr")

model = AutoModelWithLMHead.from_pretrained("cedpsam/chatbot_fr")
global_history=[]
def chat(message, history):

    history = history or global_history
    prev="\n".join([""f"{a}\n{b}" for a ,b in global_history])
    bot_input_ids=tokenizer.encode(f"{prev}\n {message}" + tokenizer.eos_token, return_tensors='pt')
    chat_history_ids = model.generate(
        bot_input_ids, max_length=80,
        pad_token_id=tokenizer.eos_token_id,
        top_p=0.92, top_k = 50,
        num_beams =16,
        max_time=30
    )
    response=tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
    history.append((message, response))
    
    return history, history


iface = gr.Interface(
    chat,
    ["text", "state"],
    ["chatbot", "state"],
    allow_screenshot=False,
    allow_flagging="never",
)
iface.launch()