fxmarty
/

distilbert-base-uncased-finetuned-sst-2-english-int8-static-dedicated-qdq-everywhere

Text Classification

Inference Endpoints

Model card Files Files and versions Community

Felix Marty commited on Sep 26, 2022

Commit

a98cdd1

•

1 Parent(s): 2596ac4

fix image display

Files changed (1) hide show

README.md +2 -6

README.md CHANGED Viewed

@@ -19,12 +19,8 @@ from optimum.onnxruntime import ORTModelForSequenceClassification
 model = ORTModelForSequenceClassification.from_pretrained("fxmarty/distilbert-base-uncased-finetuned-sst-2-english-int8-static-dedicated-qdq-everywhere")
 ```
-<details>
-<summary>Weights stored as int8, only DequantizeLinear nodes (model here: https://huggingface.co/fxmarty/distilbert-base-uncased-finetuned-sst-2-english-int8-static)</summary>
 ![DQ only](no_qdq.png)
-</details>
-<details>
-<summary>Weights stored as fp32, only QuantizeLinear + DequantizeLinear nodes (this model)</summary>
 ![QDQ](qdq.png)
-</details>

 model = ORTModelForSequenceClassification.from_pretrained("fxmarty/distilbert-base-uncased-finetuned-sst-2-english-int8-static-dedicated-qdq-everywhere")
 ```
+### Weights stored as int8, only DequantizeLinear nodes (model here: https://huggingface.co/fxmarty/distilbert-base-uncased-finetuned-sst-2-english-int8-static)
 ![DQ only](no_qdq.png)
+### Weights stored as fp32, only QuantizeLinear + DequantizeLinear nodes (this model)
 ![QDQ](qdq.png)