brjoey
/

CBSI-bert-base-uncased

Text Classification

central_bank_communication

Model card Files Files and versions

brjoey commited on 12 days ago

Commit

282372b

·

verified ·

1 Parent(s): 352e2d1

Update README.md

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ Check out their [paper](https://www.sciencedirect.com/science/article/abs/pii/S2
 The model is trained with the hyperparameters used by [Nițoi et al. (2023)](https://www.sciencedirect.com/science/article/abs/pii/S2214635023000230).
 In addition, different hyperparameters, seeds, and reinitialization of the first L layers were tested. The performance seems relatively stable across hyperparameter settings.
-Alongside these models, FinBERT, different versions of RoBERTa, and EconBERT were tested. The performance of the BERT-based models reported here is significantly better. In addition, fine-tuned ModernBERT versions are also available.
 ## Results
@@ -21,8 +21,9 @@ Alongside these models, FinBERT, different versions of RoBERTa, and EconBERT wer
 |------------------------------------------------------------------------|----------|----------|------|
 | [CBSI-bert-base-uncased](https://huggingface.co/brjoey/CBSI-bert-base-uncased)   | 0.88     | 0.88     | 0.49 |
 | [CBSI-bert-large-uncased](https://huggingface.co/brjoey/CBSI-bert-large-uncased) | 0.92     | 0.92     | 0.45 |
-| [CBSI-ModernBERT-base](https://huggingface.co/your-hf-org/CBSI-ModernBERT-base)   | 0.93    | 0.93    | 0.40 |
-| [CBSI-ModernBERT-large](https://huggingface.co/your-hf-org/CBSI-ModernBERT-large) | 0.91    | 0.91    | 0.53 |
 ## How to use

 The model is trained with the hyperparameters used by [Nițoi et al. (2023)](https://www.sciencedirect.com/science/article/abs/pii/S2214635023000230).
 In addition, different hyperparameters, seeds, and reinitialization of the first L layers were tested. The performance seems relatively stable across hyperparameter settings.
+Alongside these models, FinBERT, different versions of RoBERTa, and EconBERT were tested. The performance of the BERT-based models reported here is significantly better. In addition, fine-tuned [ModernBERT](https://huggingface.co/docs/transformers/main/en/model_doc/modernbert) and [CentralBank-BERT](https://huggingface.co/bilalzafar/CentralBank-BERT) versions are also available.
 ## Results
 |------------------------------------------------------------------------|----------|----------|------|
 | [CBSI-bert-base-uncased](https://huggingface.co/brjoey/CBSI-bert-base-uncased)   | 0.88     | 0.88     | 0.49 |
 | [CBSI-bert-large-uncased](https://huggingface.co/brjoey/CBSI-bert-large-uncased) | 0.92     | 0.92     | 0.45 |
+| [CBSI-ModernBERT-base](https://huggingface.co/brjoey/CBSI-ModernBERT-base)   | 0.93    | 0.93    | 0.40 |
+| [CBSI-ModernBERT-large](https://huggingface.co/brjoey/CBSI-ModernBERT-large) | 0.91    | 0.91    | 0.53 |
+| [CBSI-CentralBank-BERT](https://huggingface.co/brjoey/CBSI-CentralBank-BERT) | 0.92 | 0.92  |0.36 |
 ## How to use