sylwia-kuros
commited on
Commit
•
b7a6445
1
Parent(s):
f17adae
Update README.md
Browse files
README.md
CHANGED
@@ -2,9 +2,9 @@
|
|
2 |
license: mit
|
3 |
license_link: https://choosealicense.com/licenses/mit/
|
4 |
---
|
5 |
-
# -int4-ov
|
6 |
* Model creator: [Microsoft](https://huggingface.co/microsoft)
|
7 |
-
|
8 |
|
9 |
## Description
|
10 |
This is [phi-2](https://huggingface.co/microsoft/phi-2) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to INT4 by [NNCF](https://github.com/openvinotoolkit/nncf).
|
@@ -14,7 +14,7 @@ This is [phi-2](https://huggingface.co/microsoft/phi-2) model converted to the [
|
|
14 |
Weight compression was performed using `nncf.compress_weights` with the following parameters:
|
15 |
|
16 |
* mode: **int4_sym**
|
17 |
-
* ratio: **1**
|
18 |
* group_size: **128**
|
19 |
|
20 |
For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2024/openvino-workflow/model-optimization-guide/weight-compression.html).
|
|
|
2 |
license: mit
|
3 |
license_link: https://choosealicense.com/licenses/mit/
|
4 |
---
|
5 |
+
# phi-2-int4-ov
|
6 |
* Model creator: [Microsoft](https://huggingface.co/microsoft)
|
7 |
+
* Original model: [phi-2](https://huggingface.co/microsoft/phi-2)
|
8 |
|
9 |
## Description
|
10 |
This is [phi-2](https://huggingface.co/microsoft/phi-2) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to INT4 by [NNCF](https://github.com/openvinotoolkit/nncf).
|
|
|
14 |
Weight compression was performed using `nncf.compress_weights` with the following parameters:
|
15 |
|
16 |
* mode: **int4_sym**
|
17 |
+
* ratio: **1.0**
|
18 |
* group_size: **128**
|
19 |
|
20 |
For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2024/openvino-workflow/model-optimization-guide/weight-compression.html).
|