Chatbot Fr

🚀 A DialogGPT Model Trained on French OpenSubtitles with Custom Tokenizer

This is a DialogGPT model trained on French OpenSubtitles using a custom tokenizer. It offers a great solution for building French - based conversational AI applications.

Tags

• Conversational

Widget Examples

• "bonjour."
• "mais encore"
• "est ce que l'argent achete le bonheur?"

This model was trained using this notebook: Training Notebook

The configuration is based on microsoft/DialoGPT - medium. The dataset was generated from the 2018 OpenSubtitle downloaded from OPUS following these guidelines: [Dataset Guidelines](https://github.com/PolyAI - LDN/conversational - datasets/tree/master/opensubtitles) And this notebook was used for dataset generation: Dataset Generation Notebook

🚀 Quick Start

✨ Features

• This is a DialogGPT model trained on French OpenSubtitles.
• It uses a custom tokenizer.
• The configuration is based on microsoft/DialoGPT - medium.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoTokenizer, AutoModelWithLMHead

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

model = AutoModelWithLMHead.from_pretrained("cedpsam/chatbot_fr")

for step in range(6):
    # encode the new user input, add the eos_token and return a tensor in Pytorch
    new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
    # print(new_user_input_ids)

    # append the new user input tokens to the chat history
    bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids

    # generated a response while limiting the total chat history to 1000 tokens, 
    chat_history_ids = model.generate(
        bot_input_ids, max_length=1000,
        pad_token_id=tokenizer.eos_token_id,
        top_p=0.92, top_k = 50
    )
    
    # pretty print last ouput tokens from bot
    print("DialoGPT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))

Advanced Usage

No advanced usage examples are provided in the original document.

📚 Documentation

No detailed documentation other than the usage example is provided in the original document.

🔧 Technical Details

No specific technical details are provided in the original document.

📄 License

No license information is provided in the original document.