Hugging Face's logo

Intel
/
distilbert-base-uncased-finetuned-conll03-english-int8-static-inc

Token Classification
Transformers
PyTorch
English
distilbert
token-classfication
int8
Intel® Neural Compressor
PostTrainingStatic
Eval Results
Model card Files Community
xinhe commited on
Commit
75634b2
·
1 Parent(s): 55df0c9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -42,7 +42,7 @@ The calibration dataloader is the train dataloader. The default calibration samp
42
  | |INT8|FP32|
43
  |---|:---:|:---:|
44
  | **Throughput (samples/sec)** |148.144|77.108|
45
- | **Accuracy (eval-f1)** |0.9859|0.9882|
46
  | **Model size (MB)** |64.5|253|
47
 
48
  ### Load with Intel® Neural Compressor (build from source):
 
42
  | |INT8|FP32|
43
  |---|:---:|:---:|
44
  | **Throughput (samples/sec)** |148.144|77.108|
45
+ | **Accuracy (eval-accuracy)** |0.9859|0.9882|
46
  | **Model size (MB)** |64.5|253|
47
 
48
  ### Load with Intel® Neural Compressor (build from source):