Intel
/

bert-base-uncased-squadv1.1-sparse-80-1x4-block-pruneofa

Question Answering

Inference Endpoints

Model card Files Files and versions Community

bconsolvo commited on Apr 7, 2023

Commit

089f628

·

1 Parent(s): ede3f84

Update README.md

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -6,7 +6,7 @@ language: en
 license: apache-2.0
 model-index:
 - name: dynamic-tinybert
-  results:
   - task:
       type: question-answering
       name: question-answering
@@ -15,6 +15,8 @@ model-index:
       value: 81.2867
     - type: f1
       value: 88.4735
 ---
 ## Model Details: 80% 1x4 Block Sparse BERT-Base (uncased) Fine Tuned on SQuADv1.1
 This model has been fine-tuned for the NLP task of question answering, trained on the SQuAD 1.1 dataset. It is a result of fine-tuning a Prune Once For All 80% 1x4 block sparse pre-trained BERT-Base model, combined with knowledge distillation.

 license: apache-2.0
 model-index:
 - name: dynamic-tinybert
+  results:
   - task:
       type: question-answering
       name: question-answering
       value: 81.2867
     - type: f1
       value: 88.4735
+datasets:
+- squad
 ---
 ## Model Details: 80% 1x4 Block Sparse BERT-Base (uncased) Fine Tuned on SQuADv1.1
 This model has been fine-tuned for the NLP task of question answering, trained on the SQuAD 1.1 dataset. It is a result of fine-tuning a Prune Once For All 80% 1x4 block sparse pre-trained BERT-Base model, combined with knowledge distillation.