Description

The Expert_Baike_Word2vec_11B_zh model was trained among 9 domain-specific Chinese corpuses based on baike26gnews13gnovel_229g. The domain-specific corpuses have 4500 Chinese words in total (tokenized by jieba).

Usage

from gensim.models import Word2vec, KeyedVectors
pretrained_model_path = 'path/to/model'
pretrained_model = Word2vec.load(pretrained_model_path)