Sentence Similarity
sentence-transformers
PyTorch
Safetensors
Transformers
Chinese
ernie
feature-extraction
text2vec
Instructions to use shibing624/text2vec-base-chinese-paraphrase with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use shibing624/text2vec-base-chinese-paraphrase with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("shibing624/text2vec-base-chinese-paraphrase") sentences = [ "那是 個快樂的人", "那是 條快樂的狗", "那是 個非常幸福的人", "今天是晴天" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use shibing624/text2vec-base-chinese-paraphrase with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("shibing624/text2vec-base-chinese-paraphrase") model = AutoModel.from_pretrained("shibing624/text2vec-base-chinese-paraphrase", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
File size: 602 Bytes
c6e875c | 1 2 3 4 5 6 7 8 9 10 11 | global_step,train_loss,eval_spearman,eval_pearson
726,4.268328666687012,0.4961976634488731,0.5098699767582849
1452,4.030226707458496,0.5165544906672884,0.5108012677326882
2178,3.929202079772949,0.5216436974718923,0.5312741671915948
2904,3.562161684036255,0.5470897314949114,0.5322684862992731
3630,3.8007586002349854,0.5521789382995153,0.5280511704101458
4356,3.7629058361053467,0.5750803689202325,0.5509343153593886
5082,3.2100651264190674,0.5547235417018171,0.5438526474709305
5808,3.0945613384246826,0.557268145104119,0.5373790240653944
6534,3.2587833404541016,0.5623573519087228,0.5427030620948493
|