Sentence Similarity
sentence-transformers
Safetensors
English
bert
feature-extraction
sts
embeddings
symmetric-augmentation
fine-tuned
text-embeddings-inference
Instructions to use blueprint-ai/SymSTS-MiniLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use blueprint-ai/SymSTS-MiniLM with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("blueprint-ai/SymSTS-MiniLM") 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
π SymSTS-MiniLM now has a live demo!
#1
pinned
by blueprint-ai - opened
Hey everyone β you can now try SymSTS-MiniLM directly in your browser, no code needed:
π https://huggingface.co/spaces/blueprint-ai/symsts-minilm-demo
Quick recap: it's a 22.7M param sentence-similarity model that beats several bigger models (up to 109M params) on STS benchmarks β full numbers and training details are on the model card above.
Found a bug, weird output, or have feedback? Report it here in Discussions, or email blueprintai.help1@gmail.com.
Thanks for checking it out! π
blueprint-ai locked this discussion
blueprint-ai unlocked this discussion
blueprint-ai locked this discussion
blueprint-ai unlocked this discussion
blueprint-ai pinned discussion