SamLowe
/

roberta-base-go_emotions

Text Classification

multi-class-classification

multi-label-classification

Inference Endpoints

Model card Files Files and versions Community

SamLowe commited on Oct 4, 2023

Commit

58b6c5b

•

1 Parent(s): 5228df9

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ widget:
 Model trained from [roberta-base](https://huggingface.co/roberta-base) on the [go_emotions](https://huggingface.co/datasets/go_emotions) dataset for multi-label classification.
-#### ONNX
 A version of this model in ONNX format (including an INT8 quantized ONNX version) is now available at [https://huggingface.co/SamLowe/roberta-base-go_emotions-onnx](https://huggingface.co/SamLowe/roberta-base-go_emotions-onnx). These are faster for inference, esp for smaller batch sizes, massively reduce the size of the dependencies required for inference, make inference of the model more multi-platform, and in the case of the quantized version reduce the model file/download size by 75% whilst retaining almost all the accuracy if you only need inference.

 Model trained from [roberta-base](https://huggingface.co/roberta-base) on the [go_emotions](https://huggingface.co/datasets/go_emotions) dataset for multi-label classification.
+##### ONNX version also available
 A version of this model in ONNX format (including an INT8 quantized ONNX version) is now available at [https://huggingface.co/SamLowe/roberta-base-go_emotions-onnx](https://huggingface.co/SamLowe/roberta-base-go_emotions-onnx). These are faster for inference, esp for smaller batch sizes, massively reduce the size of the dependencies required for inference, make inference of the model more multi-platform, and in the case of the quantized version reduce the model file/download size by 75% whilst retaining almost all the accuracy if you only need inference.