facebook
/

muppet-roberta-large

Inference Endpoints

Model card Files Files and versions Community

anchit commited on Jun 28, 2021

Commit

575db83

•

1 Parent(s): f764c14

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -49,10 +49,10 @@ When fine-tuned on downstream tasks, this model achieves the following results:
 Glue test results:
-| Task | MNLI | QQP  | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE  |
-|:----:|:----:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|
-|      | 87.6 | 91.9 | 92.8 | 94.8  | 63.6 | 91.2  | 90.2 | 78.7 |
 ### BibTeX entry and citation info

 Glue test results:
+| Model | MNLI | QQP  | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE  | SQuAD|
+|:----:|:----:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|:----:|
+|  Roberta-large    | 90.2 | 92.2 | 94.7 | 96.4  | 63.6 | 91.2  | 90.9 | 88.1 | 88.7|
+|  MUPPET Roberta-large    | 90.8 | 92.2 | 94.9 | 97.4  | - | -  | 91.4 | 92.8 | 89.4|
 ### BibTeX entry and citation info