Update README.md
Browse files
README.md
CHANGED
@@ -35,12 +35,8 @@ The original fp32 model comes from the fine-tuned model [bart-large-mrpc](https:
|
|
35 |
|
36 |
### Test result
|
37 |
|
38 |
-
- Batch size = 8
|
39 |
-
- [Amazon Web Services](https://aws.amazon.com/) c6i.xlarge (Intel ICE Lake: 4 vCPUs, 8g Memory) instance.
|
40 |
-
|
41 |
| |INT8|FP32|
|
42 |
|---|:---:|:---:|
|
43 |
-
| **Throughput (samples/sec)** |6.529|3.261|
|
44 |
| **Accuracy (eval-f1)** |0.9051|0.9120|
|
45 |
| **Model size (MB)** |547|1556.48|
|
46 |
|
|
|
35 |
|
36 |
### Test result
|
37 |
|
|
|
|
|
|
|
38 |
| |INT8|FP32|
|
39 |
|---|:---:|:---:|
|
|
|
40 |
| **Accuracy (eval-f1)** |0.9051|0.9120|
|
41 |
| **Model size (MB)** |547|1556.48|
|
42 |
|