Downloads · 30 days
0
bg_floret_vectors_lg
sakelariev/bg_floret_vectors_lg
bg_floret_vectors_lg is a token classification model from sakelariev. Use it when you need labels on individual words, such as names. It is set up for spacy. The card lists the license as mit.
Bulgarian word vectors for a Bulgarian Spacy model.
Access
Public
Updated Oct 15, 2023
Repo size
4.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.9 GB · 47%
At a glance
- Task
- Token Classification
- Library
- spacy
- License
- mit
- Access
- Public
- Created
- Oct 12, 2023
- Updated
- Oct 15, 2023
- SHA
- ad6a9a88
Model card
From the Hugging Face model README
Bulgarian word vectors for a Bulgarian Spacy model.
The floret vectors are trained on the Oscar 21.09 corpus and Bulgarian Wikipedia pages using with the following hyperparameters: floret cbow -dim 300 -mode floret -bucket 200000 -minn 4 -maxn 5 -minCount 20 -neg 10 -hashCount 2 -lr 0.05 -thread 8
| Feature | Description |
|---|---|
| Name | bg_floret_vectors_lg |
| Version | 1.0 |
| Vectors | 200000 keys (300 dimensions) |
| Sources | OSCAR Corpus 21.09 (Julien Abadji, Pedro Ortiz Suarez), Wikipedia (bgwiki-latest-pages-articles from June 11th) |
| License | MIT |
| Author | Ivaylo Sakelariev |
- Task
- Token Classification
- Library
- spacy
- License
- mit
- Languages
- bg
- Created
- Oct 12, 2023
- Updated
- Oct 15, 2023