Downloads · 30 days
0
answerai-colbert-small-v1-onnx
lightonai/answerai-colbert-small-v1-onnx
answerai-colbert-small-v1-onnx is a feature extraction model from lightonai. Use it when you need embeddings to search or compare text. It is set up for colbert-onnx. The card lists the license as mit.
ONNX export of answerdotai/answerai-colbert-small-v1 for fast CPU inference.
Access
Public
Updated Jan 22, 2026
Repo size
167 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.onnx167 MB · 100%
At a glance
- Task
- Feature Extraction
- Library
- colbert-onnx
- License
- mit
- Access
- Public
- Created
- Jan 22, 2026
- Updated
- Jan 22, 2026
- SHA
- 8a08e612
Model card
From the Hugging Face model README
answerai-colbert-small-v1-onnx
ONNX export of answerdotai/answerai-colbert-small-v1 for fast CPU inference.
Model Details
- Source Model: answerdotai/answerai-colbert-small-v1
- Embedding Dimension: 96
- Format: ONNX (FP32 + INT8)
Files
| File | Description |
|---|---|
model.onnx | FP32 ONNX model |
model_int8.onnx | INT8 quantized model (faster) |
tokenizer.json | Tokenizer configuration |
config_sentence_transformers.json | Model configuration |
Usage with colbert-onnx (Rust)
use colbert_onnx::Colbert;
let mut model = Colbert::from_pretrained("path/to/model")?;
let embeddings = model.encode_documents(&["Hello world"])?;
Export Tool
This model was exported using pylate-onnx-export:
pip install "pylate-onnx-export @ git+https://github.com/lightonai/next-plaid.git#subdirectory=onnx/python"
pylate-onnx-export answerdotai/answerai-colbert-small-v1 --push-to-hub lightonai/answerai-colbert-small-v1-onnx
- Task
- Feature Extraction
- Library
- colbert-onnx
- License
- mit
- Created
- Jan 22, 2026
- Updated
- Jan 22, 2026