Hugging Face's logo

Intel
/
distilbert-base-uncased-finetuned-sst-2-english-int8-dynamic-inc

Text Classification Transformers PyTorch ONNX
English distilbert neural-compressor text-classfication int8 8-bit precision Intel® Neural Compressor Inference Endpoints
Model card Files Community
yuwenz commited on
Commit
532f947
•
1 Parent(s): 4bf1435

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -48,7 +48,7 @@ The original fp32 model comes from the fine-tuned model [DistilBERT](https://hug
48
 
49
  | |INT8|FP32|
50
  |---|:---:|:---:|
51
- | **Accuracy (eval-f1)** |0.9037|0.9106|
52
  | **Model size (MB)** |73|256|
53
 
54
  #### Load ONNX model:
48
 
49
  | |INT8|FP32|
50
  |---|:---:|:---:|
51
+ | **Accuracy (eval-accuracy)** |0.9037|0.9106|
52
  | **Model size (MB)** |73|256|
53
 
54
  #### Load ONNX model: