mahan_ym commited on
Commit ·
28df31a
1
Parent(s): f305549
added link to github
Browse files
README.md
CHANGED
|
@@ -39,6 +39,9 @@ BioCLIP-2 Quantized is a quantized version of BioCLIP-2, a foundation model for
|
|
| 39 |
## Model Description
|
| 40 |
BioCLIP-2 Quantized is dynamically quantized from the original BioCLIP-2 model. The Pytorch `onnx.export` function is used to convert the original model to ONNX format, and then the `onnxruntime.quantization.quantize_dynamic` function is used to perform dynamic quantization on the ONNX model with `weight_type` set to `QuantType.QInt8`.
|
| 41 |
|
|
|
|
|
|
|
|
|
|
| 42 |
## Inference
|
| 43 |
To use the quantized model for inference, you can use the `onnxruntime` library. Here is an example code snippet:
|
| 44 |
|
|
|
|
| 39 |
## Model Description
|
| 40 |
BioCLIP-2 Quantized is dynamically quantized from the original BioCLIP-2 model. The Pytorch `onnx.export` function is used to convert the original model to ONNX format, and then the `onnxruntime.quantization.quantize_dynamic` function is used to perform dynamic quantization on the ONNX model with `weight_type` set to `QuantType.QInt8`.
|
| 41 |
|
| 42 |
+
## Quantization Details
|
| 43 |
+
You can find the quantization script [here](https://github.com/mahan-ym/BioClip2_Mobile/tree/master).
|
| 44 |
+
|
| 45 |
## Inference
|
| 46 |
To use the quantized model for inference, you can use the `onnxruntime` library. Here is an example code snippet:
|
| 47 |
|