Update README.md
Browse files
README.md
CHANGED
|
@@ -109,6 +109,11 @@ When fine-tuned on those datasets, this model (the first row of the table) achie
|
|
| 109 |
|
| 110 |
To conclude, this ConvBERT model wins the ELECTRA model while losing to other models but is still fairly competitive compared to our roberta-large models when taking into account that this ConvBERT model has 106M parameters when roberta-large models have 355M parameters. ConvBERT winning the ELECTRA is also in line with the findings of the [ConvBERT paper](https://arxiv.org/abs/2008.02496).
|
| 111 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 112 |
## Team Members
|
| 113 |
|
| 114 |
- Aapo Tanskanen, [Hugging Face profile](https://huggingface.co/aapot), [LinkedIn profile](https://www.linkedin.com/in/aapotanskanen/)
|
|
|
|
| 109 |
|
| 110 |
To conclude, this ConvBERT model wins the ELECTRA model while losing to other models but is still fairly competitive compared to our roberta-large models when taking into account that this ConvBERT model has 106M parameters when roberta-large models have 355M parameters. ConvBERT winning the ELECTRA is also in line with the findings of the [ConvBERT paper](https://arxiv.org/abs/2008.02496).
|
| 111 |
|
| 112 |
+
## Acknowledgements
|
| 113 |
+
|
| 114 |
+
This project would not have been possible without compute generously provided by Google through the
|
| 115 |
+
[TPU Research Cloud](https://sites.research.google/trc/).
|
| 116 |
+
|
| 117 |
## Team Members
|
| 118 |
|
| 119 |
- Aapo Tanskanen, [Hugging Face profile](https://huggingface.co/aapot), [LinkedIn profile](https://www.linkedin.com/in/aapotanskanen/)
|