Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
dense
Generated from Trainer
dataset_size:82069
loss:MSELoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use NetherQuartz/paraphrase-MiniLM-tokipona with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use NetherQuartz/paraphrase-MiniLM-tokipona with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("NetherQuartz/paraphrase-MiniLM-tokipona") sentences = [ "Kendi kendine yardım etsen Tanrı da sana yardımcı olur.", "nasin sina li pona seme?", "ona li jan sona.", "o pana e pona tawa sama sina la mama sewi li pana e pona tawa sina." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| epoch,steps,src2trg,trg2src | |
| 1.558846453624318,2000,0.6219826576048746,0.4987110382001406 | |
| 3.117692907248636,4000,0.6707288493086477,0.5870635106632295 | |
| 4.676539360872954,6000,0.6852589641434262,0.6102648230606984 | |
| 6.235385814497272,8000,0.6878368877431451,0.6170611670963206 | |
| 7.79423226812159,10000,0.6911178814155144,0.6252636512772439 | |
| 9.353078721745907,12000,0.6934614483243496,0.6313569252402156 | |
| 10.911925175370225,14000,0.691820951488165,0.6346379189125849 | |
| 12.0,15396,0.691820951488165,0.6346379189125849 | |