lambdaofgod/paperswithcode_word2vec
This is a sentence-transformers model: It maps sentences & paragraphs to a 200 dimensional dense vector space and can be used for tasks like clustering or semantic search.
Training
This model was trained on PapersWithCode dataset on abstracts and READMEs using gensim.
Usage (Sentence-Transformers)
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('lambdaofgod/paperswithcode_word2vec')
embeddings = model.encode(sentences)
print(embeddings)
Full Model Architecture
SentenceTransformer(
(0): WordEmbeddings(
(emb_layer): Embedding(147043, 200)
)
(1): Pooling({'word_embedding_dimension': 200, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
from sentence_transformers import SentenceTransformer model = SentenceTransformer("lambdaofgod/paperswithcode_word2vec") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]