Downloads · 30 days
140K
6% of all-time downloads
Splade_PP_en_v1
Qdrant/Splade_PP_en_v1
Splade_PP_en_v1 is a sentence similarity model from Qdrant. Use it when you need a score for how close two texts are. It is set up for transformers. The card lists the license as apache-2.0.
ONNX port of prithivida/SpladePPenv1 for text classification and similarity searches.
All-time downloads
2.4M
Public
Repo size
532 MB
Likes
8
Public
Repo makeup
Click a slice to open those files.
.onnx532 MB · 100%
At a glance
- Task
- Sentence Similarity
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Mar 13, 2024
- Updated
- Sep 27, 2026
- SHA
- 600ce23f
Model card
From the Hugging Face model README
ONNX port of prithivida/Splade_PP_en_v1 for text classification and similarity searches.
Usage
Here's an example of performing inference using the model with FastEmbed.
from fastembed import SparseTextEmbedding
documents = [
"You should stay, study and sprint.",
"History can only prepare us to be surprised yet again.",
]
model = SparseTextEmbedding(model_name="prithivida/Splade_PP_en_v1")
embeddings = list(model.embed(documents))
# [
# SparseEmbedding(values=array(
# [0.45940185, 0.64054322, 0.2425732, 0.1623179, 1.20566428,
# 0.62039357...]),
# indices=array([1012, 1998, 2000, 2005, 2017, 2022...])),
# SparseEmbedding(values=array([
# 0.09767706, 0.4374367, 0.00468039, 1.01167965, 1.02318227, 1.30155718
# ...]),
# indices=array([2017, 2022, 2025, 2057, 2064, 2069...]))
# ]
- Task
- Sentence Similarity
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Mar 13, 2024
- Updated
- Sep 27, 2026