Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,18 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
Original model: https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct
|
| 6 |
+
|
| 7 |
+
Quantitation documentation: https://docs.openvino.ai/nightly/notebooks/qwen2-vl-with-output.html
|
| 8 |
+
|
| 9 |
+
Quantitation config:
|
| 10 |
+
```python
|
| 11 |
+
import nncf
|
| 12 |
+
|
| 13 |
+
compression_configuration = {
|
| 14 |
+
"mode": nncf.CompressWeightsMode.INT4_ASYM,
|
| 15 |
+
"group_size": 128,
|
| 16 |
+
"ratio": 0.5,
|
| 17 |
+
}
|
| 18 |
+
```
|