Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:86807
loss:CosineSimilarityLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use deedcon/bi-encoder-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use deedcon/bi-encoder-v2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("deedcon/bi-encoder-v2") sentences = [ "[CLS] [KNOWLEDGE] NLTK [CTX] Programmierung einer pre-processing CI/CD Pipeline zur automatisierten Verarbeitung von Newsartikeln von Tamil zu Englisch, in Python unter Verwendung von NLTK und SpaCy\n [SEP]", "[CLS] [KNOWLEDGE] SPOC [CTX] Single Point of Contact (SPOC) für die Business Units (Schnittstellenfunktion zu anderen Teilprojekten und Teams)\n [SEP]", "[CLS] [KNOWLEDGE] DIN 50001 [CTX] Mitarbeit zur Einführung eines Energiemanagementsystems nach DIN 50001\n [SEP]", "[CLS] [KNOWLEDGE] Risikomanagement [CTX] - Risikomanagement\n [SEP]" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| [ | |
| { | |
| "idx": 0, | |
| "name": "0", | |
| "path": "", | |
| "type": "sentence_transformers.models.Transformer" | |
| }, | |
| { | |
| "idx": 1, | |
| "name": "1", | |
| "path": "1_Pooling", | |
| "type": "sentence_transformers.models.Pooling" | |
| }, | |
| { | |
| "idx": 2, | |
| "name": "2", | |
| "path": "2_Normalize", | |
| "type": "sentence_transformers.models.Normalize" | |
| } | |
| ] |