cross-encoder/stsb-roberta-base
By cross-encoder · ↓ 197.9K · ♥ 5 · Updated 2025-04-11
What's in this repo
This page lists the files in cross-encoder/stsb-roberta-base, including model.onnx, model_O1.onnx, model_O2.onnx and more.
- 9 ONNX models (.onnx files)
- 25 files, including 9 .onnx, 5 .json, 3 .bin, 2 .xml, 1 .csv, 1 .md
- Repository size ~4.5 GB
- Last updated 2025-04-11
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/model.onnx | 476 MB | Download |
| onnx/model_O1.onnx | 476 MB | Download |
| onnx/model_O2.onnx | 476 MB | Download |
| onnx/model_O3.onnx | 476 MB | Download |
| onnx/model_O4.onnx | 238 MB | Download |
| onnx/model_qint8_arm64.onnx | 120 MB | Download |
| onnx/model_qint8_avx512.onnx | 120 MB | Download |
| onnx/model_qint8_avx512_vnni.onnx | 120 MB | Download |
| onnx/model_quint8_avx2.onnx | 120 MB | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
Cross-Encoder for Semantic Textual Similarity
This model was trained using SentenceTransformers Cross-Encoder class.
Training Data
This model was trained on the STS benchmark dataset. The model will predict a score between 0 and 1 how for the semantic similarity of two sentences.
Usage and Performance
Pre-trained models can be used like this:
from sentence_transformers import CrossEncoder
model = CrossEncoder('cross-encoder/stsb-roberta-base')
scores = model.predict([('Sentence 1', 'Sentence 2'), ('Sentence 3', 'Sentence 4')])
The model will predict scores for the pairs ('Sentence 1', 'Sentence 2') and ('Sentence 3', 'Sentence 4').
You can use this model also without sentence_transformers and by just using Transformers AutoModel class
Model info
Created: 2022-03-02
Updated: 2025-04-11
View on Hugging Face