mxbai-edge-colbert-v0-32m-onnx
ONNX export of mixedbread-ai/mxbai-edge-colbert-v0-32m for fast CPU inference.
Model Details
- Source Model: mixedbread-ai/mxbai-edge-colbert-v0-32m
- Embedding Dimension: 64
- 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 |
onnx_config.json |
ONNX 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 mixedbread-ai/mxbai-edge-colbert-v0-32m --quantize --push-to-hub lightonai/mxbai-edge-colbert-v0-32m-onnx