Sentence Similarity
sentence-transformers
PyTorch
Transformers
bert
feature-extraction
text-embeddings-inference
Instructions to use whaleloops/phrase-bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use whaleloops/phrase-bert with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("whaleloops/phrase-bert") 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] - Transformers
How to use whaleloops/phrase-bert with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("whaleloops/phrase-bert") model = AutoModel.from_pretrained("whaleloops/phrase-bert") - Notebooks
- Google Colab
- Kaggle
| {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home/shufanwang/.cache/torch/sentence_transformers/public.ukp.informatik.tu-darmstadt.de_reimers_sentence-transformers_v0.2_bert-base-nli-stsb-mean-tokens.zip/0_BERT/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "/home/zhichaoyang/phrase-bert/phrase-bert-model/pooled_context_para_triples_p=0.8/0_BERT", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"} |