hotchpotch
commited on
Commit
•
c7ca07e
1
Parent(s):
a4a8b62
Update README.md
Browse files
README.md
CHANGED
@@ -29,6 +29,13 @@ The model was quantized using the [optimum](https://github.com/huggingface/optim
|
|
29 |
</component>
|
30 |
```
|
31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
|
33 |
## Tips: conver to int8 quantized
|
34 |
|
@@ -60,8 +67,6 @@ model_fp16 = convert_float_to_float16(onnx_model, disable_shape_infer=True)
|
|
60 |
onnx.save(model_fp16, "me5-large/intfloat-multilingual-e5-large_fp16.onnx")
|
61 |
```
|
62 |
|
63 |
-
|
64 |
-
|
65 |
## License
|
66 |
|
67 |
The license for this model is based on the original license (found in the LICENSE file in the project's root directory), which is the MIT License.
|
|
|
29 |
</component>
|
30 |
```
|
31 |
|
32 |
+
### deploy
|
33 |
+
|
34 |
+
```
|
35 |
+
# FP16 model has a larger file size, which can result in longer deployment times.
|
36 |
+
vespa deploy --wait 1800 .
|
37 |
+
```
|
38 |
+
|
39 |
|
40 |
## Tips: conver to int8 quantized
|
41 |
|
|
|
67 |
onnx.save(model_fp16, "me5-large/intfloat-multilingual-e5-large_fp16.onnx")
|
68 |
```
|
69 |
|
|
|
|
|
70 |
## License
|
71 |
|
72 |
The license for this model is based on the original license (found in the LICENSE file in the project's root directory), which is the MIT License.
|