[Lenta Word2Vec CBOW 300D]
๐๏ธ Corpus
109k+ words from lenta.ru (2025)
โ๏ธ ะะฐัะฐะผะตััั
- Algorithm: Word2Vec CBOW
- Vector size: 300
- Window size: 10
- Min frequency: 10
๐ Metrics
- Word analogy accuracy: 42.86%
- Semantic similarity correlation: 0.18
- Vocabulary coverage: 28.76%
๐ป Use case
from gensim.models import Word2Vec
model = Word2Vec.load("lenta_w2v_cbow_300d.model")
similar = model.wv.most_similar("ะฟััะธะฝ")
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support