nbroad
/

deberta-v3-xsmall-squad2

Question Answering

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

nbroad HF staff commited on Feb 4, 2022

Commit

b2d15c1

•

1 Parent(s): 113e11a

change dataset type and readme

Files changed (1) hide show

README.md +5 -3

README.md CHANGED Viewed

@@ -22,8 +22,8 @@ model-index:
       name: Question Answering
       type: question-answering
     dataset:
-      name: squad_v2
-      type: squad_v2
     metrics:
        - name: f1
          type: f1
@@ -36,4 +36,6 @@ model-index:
 # DeBERTa v3 xsmall SQuAD 2.0
-[Microsoft reports that this model can get 84.8/82.0](https://huggingface.co/microsoft/deberta-v3-xsmall#fine-tuning-on-nlu-tasks) on f1/em on the dev set. I got 81.5/78.3 but I only did one run.

       name: Question Answering
       type: question-answering
     dataset:
+      name: SQuAD2.0
+      type: question-answering
     metrics:
        - name: f1
          type: f1
 # DeBERTa v3 xsmall SQuAD 2.0
+[Microsoft reports that this model can get 84.8/82.0](https://huggingface.co/microsoft/deberta-v3-xsmall#fine-tuning-on-nlu-tasks) on f1/em on the dev set.
+I got 81.5/78.3 but I only did one run and I didn't use the official squad2 evaluation script. I will do some more runs and show the results on the official script soon.