Sentence Similarity
sentence-transformers
Safetensors
feature-extraction
dense
Generated from Trainer
dataset_size:1000
loss:MultipleNegativesRankingLoss
Instructions to use ndsanjana/embedgemma_ns with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use ndsanjana/embedgemma_ns with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("ndsanjana/embedgemma_ns") sentences = [ "Theme: Dystopian surveillance and control, Ethical implications of autonomous warfare, Human agency versus machine dominance, Resistance against dehumanization, Unintended consequences of technological advancement, Manipulation and hidden agendas, Redemption and moral choice", "Theme: Discovery of ancient mysteries, Conflict between community values and greed, Sacrifice for the greater good, Renewal and hope through art, The power of collective action", "unknown", "Theme: AI-driven warfare and its ethical implications, Human agency versus technological determinism, Surveillance and the hunt for dissent, Rebellion against oppressive systems, The moral dilemma of dismantling versus repurposing destructive technology, Hidden sabotage and the foresight of architects, The fragility of global security in a tech‑centric world", "96_theme_cross" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [5, 5] - Notebooks
- Google Colab
- Kaggle