Dialogpt Medium Spanish Chitchat

🚀 DialoGPT-medium-spanish-chitchat

This is a transformer-decoder GPT-2 model adapted for single-turn dialogue tasks in Spanish, offering professional-style conversations.

🚀 Quick Start

This is a transformer-decoder GPT-2 model, adapted for the single-turn dialogue task in Spanish. We fine-tuned a DialoGPT-medium 345M parameter model from Microsoft, following the CLM (Causal Language Modelling) objective.

✨ Features

• Adapted for single - turn dialogue in Spanish.
• Fine - tuned from a 345M parameter DialoGPT - medium model.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

CHAT_TURNS = 5
MAX_LENGTH = 1000

model = AutoModelForCausalLM.from_pretrained('ITG/DialoGPT-medium-spanish-chitchat')
tokenizer = AutoTokenizer.from_pretrained('ITG/DialoGPT-medium-spanish-chitchat')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.to(device)
for i in range(CHAT_TURNS):
  user_input = input(f"Step - {i} >> user prompt ->")
  with torch.no_grad():
    # User turn, where "user_input" is the question (single-turn dialogue task)
    user_inputs_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")
    user_inputs_ids = user_inputs_ids.to(device)
    # The chat history adds the generated tokens for the answer
    chat_history = model.generate(user_inputs_ids, max_length=MAX_LENGTH, pad_token_id=tokenizer.eos_token_id)
    # decode just the last generated output tokens from the model (do not include the user prompt again)
    step_model_answer = tokenizer.decode(chat_history[:, user_inputs_ids.shape[-1]:][0], skip_special_tokens=True)
  print(f"Step - {i} >> DialoGPT-spanish model answer -> {step_model_answer}")

Advanced Usage

No advanced usage example is provided in the original document, so this part is skipped.

📚 Documentation

Examples

Single - turn generation examples from an interactive environment

Fine - tuning hyper - parameters

Fine - tuning in a different dataset or style

If you want to fine - tune your own dialogue model, we recommend you to start from the DialoGPT model. You can check the original GitHub repository.

🔧 Technical Details

• This model uses the original English - based tokenizer from GPT - 2 paper. Spanish tokenization is not considered but it has similarities in grammatical structure for encoding text. This overlap may help the model transfer its knowledge from English to Spanish. Moreover, the BPE (Byte Pair Encoding) implementation of the GPT - 2 tokenizer can assign a representation to every Unicode string. From the GPT - 2 paper:

  Since our approach can assign a probability to any Unicode string, this allows us to evaluate our LMs on any dataset regardless of pre - processing, tokenization, or vocab size.

• This model is intended to be used just for single - turn chitchat conversations in Spanish.
• This model's generation capabilities are limited to the extent of the aforementioned fine - tuning dataset.
• This model generates short answers, providing general context dialogue in a professional style for the Spanish language.

📄 License

This model is licensed under cc - by - nc - nd - 4.0.