Edit model card


Aira-2 is the second version of the Aira instruction-tuned series. Aira-2-portuguese-560M is an instruction-tuned model based on BLOOM. The model was trained with a dataset composed of prompts and completions generated synthetically by prompting already-tuned models (ChatGPT, Llama, Open-Assistant, etc).

Check our gradio-demo in Spaces.


  • Size: 559,012,864 parameters
  • Dataset: Instruct-Aira Dataset
  • Language: Portuguese
  • Number of Epochs: 3
  • Batch size: 8
  • Optimizer: torch.optim.AdamW (warmup_steps = 1e2, learning_rate = 5e-4, epsilon = 1e-8)
  • GPU: 1 NVIDIA A100-SXM4-40GB
  • Emissions: 0.80 KgCO2 (Singapore)
  • Total Energy Consumption: 1.64 kWh

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


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 AutoModelForCausalLM, AutoTokenizer
import torch

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

tokenizer = AutoTokenizer.from_pretrained('nicholasKluge/Aira-2-portuguese-560M')
aira = AutoModelForCausalLM.from_pretrained('nicholasKluge/Aira-2-portuguese-560M')


question =  input("Enter your question: ")

inputs = tokenizer(tokenizer.bos_token + question + tokenizer.sep_token,

responses = aira.generate(**inputs,	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 da Alemanha?

>>>Response 1: 🤖 A capital da Alemanha é Berlim. É a maior cidade da Alemanha e serve como centro administrativo, cultural e político da Alemanha.
>>>Response 2: 🤖 A capital da Alemanha é Berlim. É a maior cidade da Alemanha e serve como centro administrativo, cultural e político da Alemanha.


  • Hallucinations: This model can produce content that can be mistaken for truth but is, in fact, misleading or entirely false, i.e., hallucination.

  • Biases and Toxicity: This model inherits the social and historical stereotypes from the data used to train it. Given these biases, the model can produce toxic content, i.e., harmful, offensive, or detrimental to individuals, groups, or communities.

  • Repetition and Verbosity: The model may get stuck on repetition loops (especially if the repetition penalty during generations is set to a meager value) or produce verbose responses unrelated to the prompt it was given.

Cite as 🤗

  doi = {10.5281/zenodo.6989727},
  url = {https://huggingface.co/nicholasKluge/Aira-2-portuguese-560M},
  author = {Nicholas Kluge Corrêa},
  title = {Aira},
  year = {2023},
  publisher = {HuggingFace},
  journal = {HuggingFace repository},


Aira-2-portuguese-560M is licensed under the RAIL License since it is a model derived from BLOOM. See the LICENSE file for more details.

Downloads last month
Model size
559M params
Tensor type

Dataset used to train nicholasKluge/Aira-2-portuguese-560M

Space using nicholasKluge/Aira-2-portuguese-560M 1

Collection including nicholasKluge/Aira-2-portuguese-560M