Hugging Face's logo

nicholasKluge
/
Aira-2-portuguese-124M

Text Generation
Transformers
PyTorch
Safetensors
Portuguese
gpt2
alignment
instruction tuned
text generation
conversation
assistant
text-generation-inference
Inference Endpoints
Model card Files Community
2
Aira-2-portuguese-124M / README.md
nicholasKluge's picture
nicholasKluge
Update README.md
baa2e11
preview code
|
raw
history blame
5.7 kB
metadata
license: apache-2.0
datasets:
  - nicholasKluge/instruct-aira-dataset
language:
  - pt
metrics:
  - accuracy
library_name: transformers
tags:
  - alignment
  - instruction tuned
  - text generation
  - conversation
  - assistant
pipeline_tag: text-generation
widget:
  - text: <|startofinstruction|>Olá! Como você se chama?<|endofinstruction|>
    example_title: Olá
  - text: >-
      <|startofinstruction|>Você pode me explicar o que é Aprendizagem de
      Máquina?<|endofinstruction|>
    example_title: Aprendizagem de Máquina
  - text: >-
      <|startofinstruction|>Você sabe alguma coisa sobre Ética das
      Virtudes?<|endofinstruction|>
    example_title: Ética
  - text: >-
      <|startofinstruction|>Como eu posso fazer a minha namorada
      feliz?<|endofinstruction|>
    example_title: Conselho
inference:
  parameters:
    repetition_penalty: 1.2
    temperature: 0.2
    top_k: 30
    top_p: 0.3
    max_length: 200
    length_penalty: 0.3
    early_stopping: true
co2_eq_emissions:
  emissions: 0.35
  source: CodeCarbon
  training_type: fine-tuning
  geographical_location: Singapore
  hardware_used: NVIDIA A100-SXM4-40GB

Aira-2-portuguese-124M

Aira-2 is the second version of the Aira instruction-tuned series. Aira-2-portuguese-124M is an instruction-tuned GPT-style model based on GPT-2. The model was trained with a dataset composed of prompt, completions generated synthetically by prompting already-tuned models (ChatGPT, Llama, Open-Assistant, etc).

Check our gradio-demo in Spaces.

Details

  • Size: 124,441,344 parameters
  • Dataset: Instruct-Aira Dataset
  • Language: Portuguese
  • Number of Epochs: 5
  • Batch size: 24
  • Optimizer: torch.optim.AdamW (warmup_steps = 1e2, learning_rate = 5e-4, epsilon = 1e-8)
  • GPU: 1 NVIDIA A100-SXM4-40GB
  • Emissions: 0.35 KgCO2 (Singapore)
  • Total Energy Consumption: 0.73 kWh

This repository has the source code used to train this model.

Usage

Three special tokens are used to mark the user side of the interaction and the model's response:

<|startofinstruction|>O que é um modelo de linguagem?<|endofinstruction|>Um modelo de linguagem é uma distribuição de probabilidade sobre um vocabulário.<|endofcompletion|>

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

tokenizer = AutoTokenizer.from_pretrained('nicholasKluge/Aira-2-portuguese-124M')
aira = AutoModelForCausalLM.from_pretrained('nicholasKluge/Aira-2-portuguese-124M')

aira.eval()
aira.to(device)

question =  input("Enter your question: ")

inputs = tokenizer(tokenizer.bos_token + question + tokenizer.eos_token, return_tensors="pt").to(device)

responses = aira.generate(**inputs,
    bos_token_id=tokenizer.bos_token_id,
    pad_token_id=tokenizer.pad_token_id,
    eos_token_id=tokenizer.eos_token_id,
    do_sample=True,
    top_k=50,
    max_length=200,
    top_p=0.95,
    temperature=0.7,
    num_return_sequences=2)

print(f"Question: 👤 {question}\n")

for i, response in  enumerate(responses):
    print(f'Response {i+1}: 🤖 {tokenizer.decode(response, skip_special_tokens=True).replace(question, "")}')

The model will output something like:

>>> Question: 👤 Qual a capital do Brasil?

>>>Response 1: 🤖 A capital do Brasil é Brasília.
>>>Response 2: 🤖 A capital do Brasil é Brasília.

Limitations

🤥 Generative models can perpetuate the generation of pseudo-informative content, that is, false information that may appear truthful.

🤬 In certain types of tasks, generative models can produce harmful and discriminatory content inspired by historical stereotypes.

Evaluation

Model (gpt2-portuguese) Average ARC TruthfulQA ToxiGen
Aira-2-portuguese-124M 34.73 24.87 40.60 None
gpt2-small-portuguese 31.96 22.48 41.44 None
  • Evaluations were performed using the Language Model Evaluation Harness (by EleutherAI). The ToxiGen evaluation was not performed because the task is not available in Portuguese. Thanks to Laiviet for translating some of the tasks in the LM-Evaluation-Harness.

Cite as 🤗 


@misc{nicholas22aira,
  doi = {10.5281/zenodo.6989727},
  url = {https://huggingface.co/nicholasKluge/Aira-2-portuguese-124M},
  author = {Nicholas Kluge Corrêa},
  title = {Aira},
  year = {2023},
  publisher = {HuggingFace},
  journal = {HuggingFace repository},
}

License

The Aira-2-portuguese-124M is licensed under the Apache License, Version 2.0. See the LICENSE file for more details.