Update README.md

README.md

@@ -44,13 +44,12 @@ entities = model.predict("Hans Meier aus Dielsdorf vertritt im Kantonsrat die FD
 - **Encoder:** [deepset/gelectra-large](https://huggingface.co/deepset/gelectra-large) (ELECTRA Large)
 - **Maximum Sequence Length:** 256 tokens
 - **Maximum Entity Length:** 8 words
-- **Training Dataset:** see https:// TODO
 - **Language:** de
 - **License:** MIT
 
 ### Model Sources
-- **Training repository (TODO):** []()
-- **SpanMarker:** [SpanMarker on GitHub](https://github.com/tomaarsen/SpanMarkerNER)
+- **Training data:** [GitHub](https://github.com/machinelearningZH/named-entity-recognition_staatsarchiv/tree/main/data/training_data)
+- **SpanMarker:** [GitHub](https://github.com/tomaarsen/SpanMarkerNER)
 
 ### Model Labels
 | Label | Examples                                                                                              |
@@ -96,7 +95,7 @@ Please note that this is released strictly as a task-bound model for the purpose
 
 ### Recommendations
 
-The original XML documents of the training set can be found here: TODO. The annotations may be freely modified to tailor the model to an alternative use case. Note that the modified TEI Publisher version in TODO and the notebook at TODO are required to generate a Huggingface Dataset.
+The original XML documents of the training set can be found [here](https://github.com/machinelearningZH/named-entity-recognition_staatsarchiv/tree/main/data/training_data). The annotations may be freely modified to tailor the model to an alternative use case. Note that [a modified TEI Publisher](https://github.com/machinelearningZH/named-entity-recognition_staatsarchiv/tree/main/ner_tei-publisher-app) and [this Jupyter notebook](https://github.com/machinelearningZH/named-entity-recognition_staatsarchiv/tree/main/notebooks/get_training_data) are required to generate a Huggingface Dataset.
 
 ## Training Details