Update README.md
Browse files
README.md
CHANGED
|
@@ -24,7 +24,7 @@ This model is the ONNX version of [https://huggingface.co/SamLowe/roberta-base-g
|
|
| 24 |
- that has identical performance to the original transformers model
|
| 25 |
- and has the same model size (499MB)
|
| 26 |
- is faster than inference than normal Transformers, particularly for smaller batch sizes
|
| 27 |
-
- in my tests about 2x to 3x as fast for a batch size of 1 on a 8 core 11th gen i7 CPU using
|
| 28 |
|
| 29 |
### Quaantized (INT8) ONNX version
|
| 30 |
|
|
|
|
| 24 |
- that has identical performance to the original transformers model
|
| 25 |
- and has the same model size (499MB)
|
| 26 |
- is faster than inference than normal Transformers, particularly for smaller batch sizes
|
| 27 |
+
- in my tests about 2x to 3x as fast for a batch size of 1 on a 8 core 11th gen i7 CPU using ONNXRuntime
|
| 28 |
|
| 29 |
### Quaantized (INT8) ONNX version
|
| 30 |
|