Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
dense
Generated from Trainer
dataset_size:12105
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use vinay-pepakayala/embedding_model_custom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use vinay-pepakayala/embedding_model_custom with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("vinay-pepakayala/embedding_model_custom") sentences = [ "SD-V3_01_RD00.0 FORM_SD_INVOICE_EN <Banking data> VF02/ VF03 *** Only printed on the last page ***", "FSCM01 AR Accounting Create four debit dispute cases, for four approval levels in EUR/PLN/GBP for 4 different countries\nAttach backup, mark X for attachment, Create case title, Add information in Text field AR Accounting FBL5N Validate that the dispute case is created against the open line item on FBL5N.\nNote the Case ID# to find the dispute case in Dispute Management.\nCheck if automatic posting was done on a proper account linked to Special GL Indicator", "SD-V3_01_RD00.0 FORM_SD_INVOICE_EN <Company Code data on the footer> VF02/ VF03 *** Printed on all pages *** Name and address data of the issuing Company Code\n\n", "FA03_Depreciation run Recalculate Depreciation - it might be nessesary to recalculate deprec. if depreciation key has been changed (executed after depreciation run) Asset Accounting AFAR all proceed assets shouldn't have errors and changes" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "__version__": { | |
| "sentence_transformers": "5.1.2", | |
| "transformers": "4.57.1", | |
| "pytorch": "2.8.0+cu126" | |
| }, | |
| "model_type": "SentenceTransformer", | |
| "prompts": { | |
| "query": "", | |
| "document": "" | |
| }, | |
| "default_prompt_name": null, | |
| "similarity_fn_name": "cosine" | |
| } |