MoritzLaurer
/

DeBERTa-v3-xsmall-mnli-fever-anli-ling-binary

Zero-Shot Classification Transformers PyTorch ONNX Safetensors

English deberta-v2 text-classification Inference Endpoints

Model card Files Files and versions Community

MoritzLaurer HF staff commited on Jan 15, 2022

Commit

9934de3

•

1 Parent(s): 343f860

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -65,6 +65,8 @@ dataset | mnli-m-2c | mnli-mm-2c | fever-nli-2c | anli-all-2c | anli-r3-2c | lin
 --------|---------|----------|---------|----------|----------|------
 accuracy | 0.925 | 0.922 | 0.892 | 0.676 | 0.665 | 0.888
 speed (text/sec, CPU, 128 batch) | 6.0 | 6.3 | 3.0 | 5.8 | 5.0 | 7.6
 ## Limitations and bias
 Please consult the original DeBERTa paper and literature on different NLI datasets for potential biases.

 --------|---------|----------|---------|----------|----------|------
 accuracy | 0.925 | 0.922 | 0.892 | 0.676 | 0.665 | 0.888
 speed (text/sec, CPU, 128 batch) | 6.0 | 6.3 | 3.0 | 5.8 | 5.0 | 7.6
+speed (text/sec, GPU, 128 batch) | 473 | 487 | 230 | 390 | 340 | 586
 ## Limitations and bias
 Please consult the original DeBERTa paper and literature on different NLI datasets for potential biases.