app.py

from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel, PeftConfig
import torch
import gradio as gr
import json
import os
import shutil
import requests

# Define the device
device = "cuda" if torch.cuda.is_available() else "cpu"
#Define variables 
temperature=0.4
max_new_tokens=240
top_p=0.92
repetition_penalty=1.7
max_length=2048

model_name = "OpenLLM-France/Claire-7B-0.1"

tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
model = transformers.AutoModelForCausalLM.from_pretrained(model_name,
    device_map="auto",
    torch_dtype=torch.bfloat16,
    load_in_4bit=True                          # For efficient inference, if supported by the GPU card
)

# Class to encapsulate the Falcon chatbot
class FalconChatBot:
    def __init__(self, system_prompt):
        self.system_prompt = system_prompt

    def process_history(self, history):
        if history is None:
            return []
        
        # Ensure that history is a list of dictionaries
        if not isinstance(history, list):
            return []
        
        # Filter out special commands from the history
        filtered_history = []
        for message in history:
            if isinstance(message, dict):
                user_message = message.get("user", "")
                assistant_message = message.get("assistant", "")
                # Check if the user_message is not a special command
                if not user_message.startswith("Protagoniste:"):
                    filtered_history.append({"user": user_message, "assistant": assistant_message})
        return filtered_history

    def predict(self, user_message, assistant_message, history, temperature=0.4, max_new_tokens=700, top_p=0.99, repetition_penalty=1.9):

        # Process the history to remove special commands
        processed_history = self.process_history(history)
        # Combine the user and assistant messages into a conversation
        conversation = f"{self.system_prompt}\nFalcon: {assistant_message if assistant_message else ''} User: {user_message}\nFalcon:\n"
        # Encode the conversation using the tokenizer
        input_ids = tokenizer.encode(conversation, return_tensors="pt", add_special_tokens=False)
        # Generate a response using the Falcon model
        response = peft_model.generate(input_ids=input_ids, max_length=max_length, use_cache=False, early_stopping=False, bos_token_id=peft_model.config.bos_token_id, eos_token_id=peft_model.config.eos_token_id, pad_token_id=peft_model.config.eos_token_id, temperature=0.4, do_sample=True)
        # Decode the generated response to text
        response_text = tokenizer.decode(response[0], skip_special_tokens=True)
        # Append the Falcon-like conversation to the history
        self.history.append(conversation)
        self.history.append(response_text)
         
        return response_text


# Create the Falcon chatbot instance
falcon_bot = FalconChatBot()

# Define the Gradio interface
title = "👋🏻Bienvenue à Tonic's 🌜🌚Claire Chat !"
description = "Vous pouvez utiliser [🌜🌚ClaireGPT](https://huggingface.co/OpenLLM-France/Claire-7B-0.1) Ou dupliquer pour l'uiliser localement ou sur huggingface! [Join me on Discord to build together](https://discord.gg/VqTxc76K3u)."
history = [
     {"user": "Le dialogue suivant est une conversation entre Emmanuel Macron et Elon Musk:", "assistant": "Emmanuel Macron: Bonjour Monsieur Musk. Je vous remercie de me recevoir aujourd'hui."},]
examples = [
    [
        {
             "user_message": "[Elon Musk:] - Bonjour Emmanuel. Enchanté de vous revoir.",
             "assistant_message": "[Emmanuel Macron:] - Je vois que vous avez effectué un voyage dans la région de la Gascogne.",
             "history": [],
             "temperature": 0.4,
            "max_new_tokens": 700,
            "top_p": 0.90,
            "repetition_penalty": 1.9,
       }
   ]
]

additional_inputs=[
    gr.Textbox("", label="Introduisez Un Autre Personnage Ici ou Mettez En Scene"),
    gr.Slider(
        label="Temperature",
        value=0.9,
        minimum=0.0,
        maximum=1.0,
        step=0.05,
        interactive=True,
        info="Higher values produce more diverse outputs",
    ),
    gr.Slider(
        label="Max new tokens",
        value=256,
        minimum=0,
        maximum=3000,
        step=64,
        interactive=True,
        info="The maximum numbers of new tokens",
    ),
    gr.Slider(
        label="Top-p (nucleus sampling)",
        value=0.90,
        minimum=0.01,
        maximum=0.99,
        step=0.05,
        interactive=True,
        info="Higher values sample more low-probability tokens",
    ),
    gr.Slider(
        label="Repetition penalty",
        value=1.2,
        minimum=1.0,
        maximum=2.0,
        step=0.05,
        interactive=True,
        info="Penalize repeated tokens",
    )
]

iface = gr.Interface(
    fn=falcon_bot.predict,
    title=title,
    description=description,
#    examples=examples,
    inputs=[
        gr.inputs.Textbox(label="Utilisez se format pour initier une conversation [Personage:]", type="text", lines=5),
    ] + additional_inputs,
    outputs="text",
    theme="ParityError/Anime"
)

# Launch the Gradio interface for the Falcon model
iface.launch()