Sentence Similarity
sentence-transformers
Safetensors
Italian
mistral
feature-extraction
Generated from Trainer
dataset_size:319227
loss:MatryoshkaLoss
loss:CachedMultipleNegativesRankingLoss
dataset_size:733474
text-embeddings-inference
Instructions to use ancc/Velvet-2B-Embedding-1004 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use ancc/Velvet-2B-Embedding-1004 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("ancc/Velvet-2B-Embedding-1004") sentences = [ "Jovanotti torna con Fuorionda : ma come fa a inventarsene sempre una?", "Migros Ticino: «Non vediamo segni di ripresa, ma puntiamo su investimenti e nuove aperture", "Jovanotti canta i “Fuorionda” della vita: “Andiamo avanti, siamo sempre all’inizio di qualcosa”", "WTA Indian Wells, Swiatek: \"Ci sono vari modi di sfruttare il vento\"" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download modules.json from ancc/Velvet-2B-Embedding-1004: direct link, hf CLI and curl.
- Browser
- Download file 349 Bytes
-
https://huggingface.co/ancc/Velvet-2B-Embedding-1004/resolve/main/modules.json
- Command line
-
hf download hf://ancc/Velvet-2B-Embedding-1004/modules.json
-
curl -L -o modules.json https://huggingface.co/ancc/Velvet-2B-Embedding-1004/resolve/main/modules.json
349 Bytes
| [ | |
| { | |
| "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" | |
| } | |
| ] |