Sentence Similarity
sentence-transformers
Safetensors
Slovak
xlm-roberta
feature-extraction
dense
Generated from Trainer
dataset_size:137745
loss:CosineSimilarityLoss
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use borsimnet/e5-sk-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use borsimnet/e5-sk-large with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("borsimnet/e5-sk-large") sentences = [ "Mor a epidémia sa očividne vymkli spod kontroly .", "Choroba bola nekontrolovateľná a ohrozovala všetok život .", "Tieto vylúčenia sú určené na iné cieľové skupiny ako obchodné štvrte .", "Autobus National Trust Tour odchádza každý deň o 9:00 z National Trust Information Centre ." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
File size: 499 Bytes
7d86055 | 1 2 3 4 5 | epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision,cosine_recall,cosine_f1_threshold,cosine_ap,cosine_mcc
1.0,60,0.5234657039711191,0.6437346437346437,0.4746376811594203,1.0,0.36661099711724937,0.05701704150199188
2.0,120,0.5234657039711191,0.6403940886699507,0.4727272727272727,0.9923664122137404,0.3703334021795854,-0.004624851991046135
3.0,180,0.5234657039711191,0.6388206388206388,0.47101449275362317,0.9923664122137404,0.37631002414169196,-0.06354571037626576
|