Sentence Similarity
sentence-transformers
PyTorch
modernbert
feature-extraction
Generated from Trainer
dataset_size:3988
loss:AnglELoss
text-embeddings-inference
Instructions to use korolewadim/gselformer-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use korolewadim/gselformer-large with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("korolewadim/gselformer-large") sentences = [ "C C =Branch1 C =O N C C N Branch2 Ring2 =C C =N N =C Branch2 Ring1 Branch1 C O C =C C =C Branch1 =Branch2 C Branch1 C C Branch1 C C C C =C Ring1 #Branch2 N Ring1 P C C C =C Branch1 C C N =C Branch1 C C S Ring1 #Branch1 C C Ring2 Ring1 S", ":0diethylamine Branch =O pop Ring2 N Branch C :=1hydrazine Ring1 :=3diethylamine Ring1 :0prop2en1ol Ring1 :=1ethane Ring1 =C Branch :2isobutane pop Ring1 Ring2 pop pop pop Branch Ring1 =Branch pop Branch C S C Branch C pop :=0ethanamine Ring1 =Ring1 =Branch pop pop pop pop :1ethane Ring1 Ring2 Ring2 =Branch pop pop", ":0ethene C C N :2ethanamine Ring1 :5propylbenzene Ring2 =O pop N Ring1 =C pop #Branch :2formimidamide Ring2 N Branch C pop Ring1 =C pop Ring2 C :1methoxymethane pop pop pop pop", ":0nitro C :1prop1ene Ring1 C :=1;2fluoroethan1ol Ring1 =Ring1 #Branch pop Ring1 :2ethanol Ring1 C =C :1ethene Ring1 :1ethene Ring1 Ring1 Branch pop pop pop pop pop pop" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Ctrl+K
This model has 1 file scanned as unsafe.