fasttext-cbow-600d

NILC Portuguese Word Embeddings — FastText CBOW 600d

This repository contains the FastText CBOW 600d model in safetensors format.

About

NILC-Embeddings is a repository for storing and sharing word embeddings for the Portuguese language. The goal is to provide ready-to-use vector resources for Natural Language Processing (NLP) and Machine Learning tasks.

The embeddings were trained on a large Portuguese corpus (Brazilian + European), composed of 17 corpora (~1.39B tokens). Training was carried out with the following algorithms: Word2Vec, FastText, Wang2Vec, and GloVe.

---

📂 Files

• embeddings.safetensors → embedding matrix ([vocab_size, 600])
• vocab.txt → vocabulary (one token per line, aligned with rows)

---

🚀 Usage

from huggingface_hub import hf_hub_download
from safetensors.numpy import load_file

path = hf_hub_download(repo_id="nilc-nlp/fasttext-cbow-600d",
                       filename="embeddings.safetensors")

data = load_file(path)
vectors = data["embeddings"]

vocab_path = hf_hub_download(repo_id="nilc-nlp/fasttext-cbow-600d",
                             filename="vocab.txt")
with open(vocab_path) as f:
    vocab = [w.strip() for w in f]

print(vectors.shape)

Or in PyTorch:

from safetensors.torch import load_file
tensors = load_file("embeddings.safetensors")
vectors = tensors["embeddings"]  # torch.Tensor

---

📊 Corpus

The embeddings were trained on a combination of 17 corpora (~1.39B tokens):

---

📖 Paper

Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks
Hartmann, N. et al. (2017), STIL 2017.
ArXiv Paper

BibTeX

@inproceedings{hartmann-etal-2017-portuguese,
  title        = {{P}ortuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks},
  author       = {Hartmann, Nathan  and Fonseca, Erick  and Shulby, Christopher  and Treviso, Marcos  and Silva, J{'e}ssica  and Alu{'i}sio, Sandra},
  year         = 2017,
  month        = oct,
  booktitle    = {Proceedings of the 11th {B}razilian Symposium in Information and Human Language Technology},
  publisher    = {Sociedade Brasileira de Computa{\c{c}}{\~a}o},
  address      = {Uberl{\^a}ndia, Brazil},
  pages        = {122--131},
  url          = {https://aclanthology.org/W17-6615/},
  editor       = {Paetzold, Gustavo Henrique  and Pinheiro, Vl{'a}dia}
}

---

📜 License

Creative Commons Attribution 4.0 International (CC BY 4.0)