Update README.md
Browse files
README.md
CHANGED
|
@@ -18,3 +18,17 @@ This model is then further pre-trained on 5 million cardiology records from the
|
|
| 18 |
model collapse, trained on 1024 maximal sequence length and linear decay with warmup, for about 1 epoch.
|
| 19 |
|
| 20 |
The perplexity was around 4 on the validation set.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
model collapse, trained on 1024 maximal sequence length and linear decay with warmup, for about 1 epoch.
|
| 19 |
|
| 20 |
The perplexity was around 4 on the validation set.
|
| 21 |
+
|
| 22 |
+
If you use this model please cite with
|
| 23 |
+
|
| 24 |
+
```bibtex
|
| 25 |
+
@misc{vanes2026languagecorporadutchmedical,
|
| 26 |
+
title={Language corpora for the Dutch medical domain},
|
| 27 |
+
author={B. van Es},
|
| 28 |
+
year={2026},
|
| 29 |
+
eprint={2604.25374},
|
| 30 |
+
archivePrefix={arXiv},
|
| 31 |
+
primaryClass={cs.CL},
|
| 32 |
+
url={https://arxiv.org/abs/2604.25374},
|
| 33 |
+
}
|
| 34 |
+
```
|