Instructions to use huspacy/hu_vectors_web_md with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- spaCy
How to use huspacy/hu_vectors_web_md with spaCy:
!pip install https://huggingface.co/huspacy/hu_vectors_web_md/resolve/main/hu_vectors_web_md-any-py3-none-any.whl # Using spacy.load(). import spacy nlp = spacy.load("hu_vectors_web_md") # Importing as module. import hu_vectors_web_md nlp = hu_vectors_web_md.load() - fastText
How to use huspacy/hu_vectors_web_md with fastText:
from huggingface_hub import hf_hub_download import fasttext model = fasttext.load_model(hf_hub_download("huspacy/hu_vectors_web_md", "model.bin")) - Notebooks
- Google Colab
- Kaggle
Hungarian word vectors for HuSpaCy.
The model is trained on the Hungarian Webcorpus 2.0 using floret with the following hyperparameters: floret cbow -dim 100 -mode floret -bucket 200000 -minn 4 -maxn 6 -minCount 100 -neg 10 -hashCount 2 -lr 0.1 -thread 30 -epoch 5
Vectors are published in fasttext and floret format.
| Feature | Description |
|---|---|
| Name | hu_vectors_web_lg |
| Version | 1.0 |
| Vectors | 200000 keys (300 dimensions) |
| Sources | Hungarian Webcorpus 2.0 (Dávid Márk Nemeskey (SZTAKI-HLT)) |
| License | cc-by-sa-4.0 |
| Author | SzegedAI, MILAB |
Accuracy
| Type | Score |
|---|---|
ACC |
10.10 |
MRR |
0.1772 |
- Downloads last month
- -
Evaluation results
- Accuracyself-reported0.101
- MRRself-reported0.177