Update README.md

README.md

@@ -32,9 +32,13 @@ inference:
 
 This model is a fine-tuned version of [NbAiLab/nb-bert-base](https://huggingface.co/NbAiLab/nb-bert-base) for Natural Language Inference in Danish, Norwegian Bokmål and Swedish.
 
-It has been fine-tuned on a dataset composed of [DanFEVER](https://aclanthology.org/2021.nodalida-main.pdf#page=439) as well as machine translated versions of [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) and [CommitmentBank](https://doi.org/10.18148/sub/2019.v23i2.601) into all three languages, and machine translated versions of [FEVER](https://aclanthology.org/N18-1074/) and [Adversarial NLI](https://aclanthology.org/2020.acl-main.441/) into Swedish.
+We have released three models for Scandinavian NLI, of different sizes:
 
-The three languages are sampled equally during training, and they're validated on validation splits of [DanFEVER](https://aclanthology.org/2021.nodalida-main.pdf#page=439) and machine translated versions of [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) for Swedish and Norwegian Bokmål, sampled equally.
+- [alexandrainst/scandi-nli-large](https://huggingface.co/alexandrainst/scandi-nli-large)
+- [alexandrainst/scandi-nli-base](https://huggingface.co/alexandrainst/scandi-nli-base)
+- [alexandrainst/scandi-nli-small](https://huggingface.co/alexandrainst/scandi-nli-small)
+
+The performance and model size of each of them can be found in the Performance section below.
 
 
 ## Quick start
@@ -69,13 +73,17 @@ We report Matthew's Correlation Coefficient (MCC), macro-average F1-score as wel
 
 | **Model** | **MCC** | **Macro-F1** | **Accuracy** | **Number of Parameters** |
 | :-------- | :------------ | :--------- | :----------- | :----------- |
-| [`alexandrainst/nb-bert-large-nli-scandi`](https://huggingface.co/alexandrainst/nb-bert-large-nli-scandi) | **73.80%** | **58.41%** | **86.98%** | 354M |
-| `alexandrainst/nb-bert-base-nli-scandi` (this) | 62.44% | 55.00% | 80.42% | 178M |
-| [`alexandrainst/electra-small-nordic-nli-scandi`](https://huggingface.co/alexandrainst/electra-small-nordic-nli-scandi) | 47.28% | 48.88% | 73.46% | **22M** |
+| [`alexandrainst/scandi-nli-large`](https://huggingface.co/alexandrainst/scandi-nli-large) | **73.80%** | **58.41%** | **86.98%** | 354M |
+| `alexandrainst/scandi-nli-base` (this) | 62.44% | 55.00% | 80.42% | 178M |
+| [`alexandrainst/scandi-nli-small`](https://huggingface.co/alexandrainst/scandi-nli-small) | 47.28% | 48.88% | 73.46% | **22M** |
 
 
 ## Training procedure
 
+It has been fine-tuned on a dataset composed of [DanFEVER](https://aclanthology.org/2021.nodalida-main.pdf#page=439) as well as machine translated versions of [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) and [CommitmentBank](https://doi.org/10.18148/sub/2019.v23i2.601) into all three languages, and machine translated versions of [FEVER](https://aclanthology.org/N18-1074/) and [Adversarial NLI](https://aclanthology.org/2020.acl-main.441/) into Swedish.
+
+The three languages are sampled equally during training, and they're validated on validation splits of [DanFEVER](https://aclanthology.org/2021.nodalida-main.pdf#page=439) and machine translated versions of [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) for Swedish and Norwegian Bokmål, sampled equally.
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training: