Sentence Similarity
sentence-transformers
PyTorch
Transformers
bert
feature-extraction
semantic-search
chinese
text-embeddings-inference
Instructions to use TaoH/dj with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use TaoH/dj with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("TaoH/dj") 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 TaoH/dj with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("TaoH/dj") model = AutoModel.from_pretrained("TaoH/dj") - Notebooks
- Google Colab
- Kaggle
| { | |
| "cls_token": "[CLS]", | |
| "do_lower_case": false, | |
| "mask_token": "[MASK]", | |
| "model_max_length": 512, | |
| "name_or_path": "/home/taohe/.cache/torch/sentence_transformers/DMetaSoul_sbert-chinese-general-v2/", | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "special_tokens_map_file": null, | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "unk_token": "[UNK]" | |
| } | |