Sentence Similarity
sentence-transformers
Safetensors
English
nomic_bert
feature-extraction
Generated from Trainer
dataset_size:35964
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
custom_code
Eval Results (legacy)
text-embeddings-inference
Instructions to use Corran/SciTopicNomicEmbed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Corran/SciTopicNomicEmbed with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Corran/SciTopicNomicEmbed", trust_remote_code=True) sentences = [ "Despite the crucial role of phosphorus in global food production, there is a lack of comprehensive analysis on the economic and policy aspects of phosphorus supply and demand, highlighting a significant knowledge gap in the field of natural resource economics.", "The human brain is intrinsically organized into dynamic, anticorrelated functional networks", "The story of phosphorus: Global food security and food for thought", "Identifying a knowledge gap in the field of study" ] 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" | |
| } | |
| ] |