Hugging Face's logo

Intel
/
bert-base-uncased-squad-int8-static-inc

Question Answering
Transformers
PyTorch
bert
int8
Intel® Neural Compressor
neural-compressor
PostTrainingStatic
Inference Endpoints
Model card Files Community
xinhe commited on
Commit
2018193
•
1 Parent(s): d349d5c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -26,7 +26,7 @@ The linear modules **bert.encoder.layer.2.intermediate.dense**, **bert.encoder.l
26
 
27
  | |INT8|FP32|
28
  |---|:---:|:---:|
29
- | **Accuracy (eval-f1)** |0.8730|0.8810|
30
  | **Model size (MB)** |139|436|
31
 
32
  ### Load with Intel® Neural Compressor:
26
 
27
  | |INT8|FP32|
28
  |---|:---:|:---:|
29
+ | **Accuracy (eval-f1)** |87.3006|88.1030|
30
  | **Model size (MB)** |139|436|
31
 
32
  ### Load with Intel® Neural Compressor: