Sentence Similarity
sentence-transformers
Safetensors
modernbert
unsloth
feature-extraction
dense
Generated from Trainer
dataset_size:761918
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use electroglyph/FictionBert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use electroglyph/FictionBert with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("electroglyph/FictionBert") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop

- Xet hash:
- f960a3e7966049807a86ab76ef9ef75f072c624483fb3c5dee4f34ec46a79c3c
- Size of remote file:
- 404 kB
- SHA256:
- 5c025b5691db5524760e312eb8ffc4246a1fe84889a85563785efc94d005b5b0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.