Update README.md

README.md

@@ -10,10 +10,14 @@ metrics:
 - accuracy
 pipeline_tag: text-classification
 widget:
-- text: "Would you like to join a major manufacturing company?"
 - text: "You must be proficient in Excel."
+- text: "Would you like to join a major manufacturing company?"
 ---
 
+_Nesta, the UK's innovation agency, has been scraping online job adverts since 2021 and have been building algorithms to extract and structure information as part of the [Open Jobs Observatory](https://www.nesta.org.uk/project/open-jobs-observatory/) project._ 
+
+_Although we are unable to share the raw data openly, we aim to open source **our models, algorithms and tools** so that anyone can use them for their own research and analysis._
+
 ## 🖊️ Model description
 
 This model is a fine-tuned version of [jjzha/jobbert-base-cased](https://huggingface.co/jjzha/jobbert-base-cased). JobBERT is a continuously pre-trained bert-base-cased checkpoint on ~3.2M sentences from job postings.
@@ -31,6 +35,8 @@ It achieves the following results on a held out test set 147 sentences:
 | not company description      | 0.930693       |0.959184|0.944724|98|
 | company description   | 0.913043        |0.857143|0.884211|49|
 
+The code for training the model is in our [ojd_daps_language_models repo](https://github.com/nestauk/ojd_daps_language_models), a central repository for fine-tuning transformer models on our database of scraped job adverts.
+
 ## 🖨️ Use
 
 To use the model: