Sentence Similarity
sentence-transformers
Safetensors
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:10189
loss:DistillationTripletLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use Data-Lab/USER-bge-m3-embedder_distill-tg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Data-Lab/USER-bge-m3-embedder_distill-tg with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Data-Lab/USER-bge-m3-embedder_distill-tg") sentences = [ "фисташки", "Батончик ореховый \"Арахис-фисташка\" батончик, орехи, арахис, фисташка, тыквенные семена, фруктоза, пребиотик, мобильный перекус, десерт, натуральные ингредиенты, лёгкий перекус", "Торт \"Белые ночи\" с сырным кремом торт, десерт, сырный крем, шоколад, глазурь, бисквит, праздничный, угощение, аллергены, домашняя выпечка", "Фисташки жареные, 1 кг None, фисташки, жареные, сладкие, закуска, орехи, скорлупа, 1 кг" ] 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" | |
| } | |
| ] |