philschmid commited on
Commit
e02999f
·
1 Parent(s): 14a60c2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -2
README.md CHANGED
@@ -26,11 +26,15 @@ model-index:
26
  This model is a statically quantized version of [optimum/distilbert-base-uncased-finetuned-banking77](https://huggingface.co/optimum/distilbert-base-uncased-finetuned-banking77) on the `banking77` dataset.
27
  It achieves the following results on the evaluation set:
28
 
 
 
29
  - Vanilla model: 92.5%
30
  - Quantized model: 92.24%
31
- => The quantized model achieves 99.72% accuracy of the fp32 model
32
 
33
- Latency
 
 
 
34
  Payload sequence length: 128
35
  Instance type: AWS c6i.xlarge
36
 
 
26
  This model is a statically quantized version of [optimum/distilbert-base-uncased-finetuned-banking77](https://huggingface.co/optimum/distilbert-base-uncased-finetuned-banking77) on the `banking77` dataset.
27
  It achieves the following results on the evaluation set:
28
 
29
+ **Accuracy**
30
+
31
  - Vanilla model: 92.5%
32
  - Quantized model: 92.24%
 
33
 
34
+ > => The quantized model achieves 99.72% accuracy of the fp32 model
35
+
36
+ **Latency**
37
+
38
  Payload sequence length: 128
39
  Instance type: AWS c6i.xlarge
40