bge-small-en-v1.5

bge-small-en-v1.5

This version of bge-small-en-v1.5 model has been converted to run on the Axera NPU using w8a16 quantization.

This model has been optimized with the following LoRA:

Compatible with Pulsar2 version: 5.0-patch1

Convert tools links:

For those who are interested in model conversion, you can try to export axmodel through

• Model Convert, which you can get the detail of guide

• Pulsar2 Link, How to Convert ONNX to axmodel

Support Platform

• AX650
  • M4N-Dock(爱芯派Pro)
  • M.2 Accelerator card

How to use

Download all files from this repository to the device

(py312) root@ax650:~/bge-small-en-v1.5# tree
.
|-- README.md
|-- model
|   |-- bge-small-en-v1.5.json
|   |-- bge-small-en-v1.5.onnx
|   `-- bge-small-en-v1.5_u16_npu3.axmodel
|-- python
|   |-- axmodel_infer.py
|   `-- onnx_infer.py
`-- requirements.txt

Inference

Inference with AX650 Host, such as M4N-Dock(爱芯派Pro)

run with python3 axmodel_infer.py

root@ax650:~/bge-small-en-v1.5# python3 axmodel_infer.py
[INFO] Available providers:  ['AxEngineExecutionProvider']
[INFO] Using provider: AxEngineExecutionProvider
[INFO] Chip type: ChipType.MC50
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Engine version: 2.12.0s
[INFO] Model type: 2 (triple core)
[INFO] Compiler version: 5.0-patch1 be1a7606
similarity: [[0.8832189]]
gt similarity: [[0.87731415]]