Intel
/

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

Text Classification

neural-compressor

text-classfication

8-bit precision

Intel® Neural Compressor

Inference Endpoints

Model card Files Files and versions Community

1pikachu1111 commited on Jun 27, 2023

Commit

b539226

•

1 Parent(s): 532f947

update int8 onnx model and readme

Signed-off-by: dujun <jun.du@intel.com>

Files changed (2) hide show

README.md +2 -2
model.onnx +2 -2

README.md CHANGED Viewed

@@ -48,8 +48,8 @@ The original fp32 model comes from the fine-tuned model [DistilBERT](https://hug
 |   |INT8|FP32|
 |---|:---:|:---:|
-| **Accuracy (eval-accuracy)** |0.9037|0.9106|
-| **Model size (MB)**  |73|256|
 #### Load ONNX model:

 |   |INT8|FP32|
 |---|:---:|:---:|
+| **Accuracy (eval-accuracy)** |0.9025|0.9106|
+| **Model size (MB)**  |165|256|
 #### Load ONNX model:

model.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffaa5bd531a044237ee88f08e97dcae85bb121806fd1a5e7c556a13927343ad4
-size 76104966

 version https://git-lfs.github.com/spec/v1
+oid sha256:f7c715993f1eb3f6a0bf49866e6c04a5c09a40374687359f12e0f27f344af446
+size 172433110