Downloads · 30 days
0
jina-colbert-v2-onnx
thlurte/jina-colbert-v2-onnx
jina-colbert-v2-onnx is a machine learning model from thlurte. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for intextus.
This repository contains the ONNX version of jinaai/jina-colbert-v2 exported specifically for the intextus accelerated C++ late-interaction engine.
Access
Public
Updated Jun 21, 2026
Repo size
2.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data2.2 GB · 99%
At a glance
- Library
- intextus
- Access
- Public
- Created
- Jun 21, 2026
- Updated
- Jun 21, 2026
- SHA
- bc4711db
Model card
From the Hugging Face model README
intextus/jina-colbert-v2-onnx
This repository contains the ONNX version of jinaai/jina-colbert-v2 exported specifically for the intextus accelerated C++ late-interaction engine.
Model Details
- Base Model:
jinaai/jina-colbert-v2 - Output Embedding Dimension: 128
- Opset Version: 18
- Exported using: PyTorch ONNX Dynamo Exporter
Usage with Intextus
from intextus import LateInteractionEncoder
model = LateInteractionEncoder("intextus/jina-colbert-v2-onnx")
q = model.encode_queries("What is late interaction?")
d = model.encode_docs("ColBERT uses late interaction with token-level representation.")
- Library
- intextus
- Created
- Jun 21, 2026
- Updated
- Jun 21, 2026