Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,8 @@ XtremeDistil is a distilled task-agnostic transformer model leveraging multi-tas
|
|
| 12 |
|
| 13 |
This l6-h384 checkpoint with **6** layers, **384** hidden size, **12** attention heads corresponds to **22 million** parameters with **5.3x** speedup over BERT-base.
|
| 14 |
|
|
|
|
|
|
|
| 15 |
The following table shows the results on GLUE dev set and SQuAD-v2.
|
| 16 |
|
| 17 |
| Models | #Params | Speedup | MNLI | QNLI | QQP | RTE | SST | MRPC | SQUAD2 | Avg |
|
|
|
|
| 12 |
|
| 13 |
This l6-h384 checkpoint with **6** layers, **384** hidden size, **12** attention heads corresponds to **22 million** parameters with **5.3x** speedup over BERT-base.
|
| 14 |
|
| 15 |
+
Other available checkpoints: [xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) and [xtremedistil-l6-h384-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h384-uncased)
|
| 16 |
+
|
| 17 |
The following table shows the results on GLUE dev set and SQuAD-v2.
|
| 18 |
|
| 19 |
| Models | #Params | Speedup | MNLI | QNLI | QQP | RTE | SST | MRPC | SQUAD2 | Avg |
|