Sentence Similarity
sentence-transformers
Safetensors
mpnet
feature-extraction
dense
Generated from Trainer
dataset_size:30705
loss:NormalizedMultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use nafis277/domain-mpnet-normalized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nafis277/domain-mpnet-normalized with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nafis277/domain-mpnet-normalized") sentences = [ "According to Mitchell et al (1997) ______, the perceived ability of a stakeholder to influence organisational action, ________ whether the organisation perceives the stakeholder's actions as desirable, proper and appropriate and ________, the immediacy of attention the stakeholder claims require, determine stakeholder ________.", "Mr. Williams, upon filing a petition for bankruptcy, stated that he had a total of only $2,240 in assets, with liabilities amounting to $5,600. How much money can Mr. Johnson, a creditor, expect to receive if he has a claim of $1,725?", "What is the difference in cost between a 3-year policy and 3 one-year policies for $22,000 worth of coverage, if the rate is $1.19 per $1,000?", "Williamsville has a total assessed valuation of property of $6,250,000.The town requires $360,000 for educational purposesand $115,000 for health and welfare needs. What isthe town's tax rate in dollars per $100." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "backend": "tokenizers", | |
| "bos_token": "<s>", | |
| "cls_token": "<s>", | |
| "do_lower_case": true, | |
| "eos_token": "</s>", | |
| "is_local": false, | |
| "mask_token": "<mask>", | |
| "max_length": 128, | |
| "model_max_length": 384, | |
| "pad_to_multiple_of": null, | |
| "pad_token": "<pad>", | |
| "pad_token_type_id": 0, | |
| "padding_side": "right", | |
| "sep_token": "</s>", | |
| "stride": 0, | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "MPNetTokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "[UNK]" | |
| } | |