Update README.md

README.md

@@ -11,14 +11,18 @@ license: "MIT"
 
 ## Model description
 
-BERT-large-uncased model, pretrained on a corpus of messages from Twitter about COVID-19
+BERT-large-uncased model, pretrained on a corpus of messages from Twitter about COVID-19. This model is identical to [covid-twitter-bert](https://huggingface.co/digitalepidemiologylab/covid-twitter-bert) - but trained on more data, resulting in higher downstream performance.
+
+Find more info on our [GitHub page](https://github.com/digitalepidemiologylab/covid-twitter-bert).
+
 
 ## Intended uses & limitations
 
+The model can be used in the `fill-mask` task (see below).
+
 #### How to use
 
 ```python
-# You can include sample code which will be formatted
 from transformers import pipeline
 import json
 
@@ -36,10 +40,6 @@ print(json.dumps(out, indent=4))
 ]
 ```
 
-## Training data
-Describe the data you used to train the model.
-If you initialized it with pre-trained weights, add a link to the pre-trained model card or repository with description of the pre-training data.
-
 ## Training procedure
 This model was trained on 97M unique tweets (1.2B training examples) collected between January 12 and July 5, 2020 containing at least one of the keywords "wuhan", "ncov", "coronavirus", "covid", or "sars-cov-2". These tweets were filtered and preprocessed to reach a final sample of 22.5M tweets (containing 40.7M sentences and 633M tokens) which were used for training.