Model Details
Full Model IDsentence-transformers/paraphrase-MiniLM-L6-v2
Pipeline / Tasksentence-similarity
Librarysentence-transformers
Downloads (all-time)3.5M
Likes148
Last Modified3/6/2025
Author / Orgsentence-transformers
PrivateNo — public
⚡ Quick Usage (Python)
Using the 🤗 Transformers library. Install with pip install transformers
from transformers import pipeline
# Load the model
pipe = pipeline("sentence-similarity", model="sentence-transformers/paraphrase-MiniLM-L6-v2")
# Run inference
result = pipe("Your input here")
print(result)🏷️ Tags
sentence-transformerspytorchtfonnxsafetensorsopenvinobertfeature-extractionsentence-similaritytransformersarxiv:1908.10084license:apache-2.0text-embeddings-inferenceendpoints_compatibleregion:us
More sentence-similarity Models
See all →🚀 Use This Model
Access model files, inference API, and full documentation on Hugging Face.
Open on Hugging Face →Browse Model Files ↗← Browse All Models🤖 Task: sentence-similarity
This model is designed for the sentence-similarity task. Explore more models for this use case.
All sentence-similarity Models →📊 Popularity
⬇ Downloads3.5M
❤️ Community Likes148
🛠️ Requirements
- →Install: pip install sentence-transformers
- →Python 3.8+ recommended for Transformers.
- →GPU (CUDA) speeds up inference significantly.
- →Use model.half() for fp16 on limited VRAM.