Update README.md

README.md

@@ -5,12 +5,45 @@ base_model:
 - KB/bert-base-swedish-cased
 pipeline_tag: text-classification
 ---
+
+<!--
+TODO:
+ - Add model description
+ - Add license
+ - Add URL to the repo
+   - Clean and comment thesis repo
+   - Publish thesis repo
+ - Add _Uses_ section
+   - Edit _Direct Use_
+   - Edit _Out-of-Scope Use_
+ - Edit _Bias, Risks, and Limitations_
+   - Edit _Recommendations_
+ - Edit _How to Get Started_
+ - Edit _Training Details_
+   - Edit _Training Data_
+   - Edit _Training Procedure_
+     - Edit _Preprocessing_
+     - Edit _Training Hyperparameters_
+ - Edit _Evaluation_
+   - Edit _Testing Data, Factors & Metrics_
+     - Edit _Testing Data_
+     - Edit _Factors_
+     - Edit _Metrics_
+   - Edit _Results_
+     - Edit _Summary_
+ - Edit _Model Examination_
+ - Edit _Environmental Impact_
+-->
+
+
 # Model Card for Model ID
 
 This model was developed as part of the [Computational SLA](https://spraakbanken.gu.se/en/projects/computational-sla) working group at Språkbanken Text.
 It takes essays written in Swedish by second language learners and assigns them one of the [CEFR levels](https://en.wikipedia.org/wiki/Common_European_Framework_of_Reference_for_Languages).
 Of note is that it only uses the first five levels of the scale (A1 to C1), ignoring level C2 due to both lack of training data and it measuring things differently than the other levels do.
 
+Most of the information contained in this Model Card comes from [the paper that introduced the present model](https://aclanthology.org/2024.nlp4call-1.11/).
+Feel free to check it out for more in-depth information.
 
 ## Model Details
 
@@ -31,9 +64,8 @@ Of note is that it only uses the first five levels of the scale (A1 to C1), igno
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
+- **Repository:** _coming soon_ <!-- Need to update and publish thesis repos -->
 - **Paper:** Jingle BERT, Jingle BERT, Frozen All the Way: Freezing Layers to Identify CEFR Levels of Second Language Learners Using BERT ([link](https://aclanthology.org/2024.nlp4call-1.11/))
-- **Demo [optional]:** [More Information Needed]
 
 ## Uses
 
@@ -75,7 +107,7 @@ Use the code below to get started with the model.
 
 <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
-[More Information Needed]
+We used essays from the SweLL-Pilot 
 
 ### Training Procedure
 
@@ -90,11 +122,6 @@ Use the code below to get started with the model.
 
 - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
 
 ## Evaluation
 
@@ -188,4 +215,6 @@ Ricardo Muñoz Sánchez ([rimusa](https://huggingface.co/rimusa))
 
 ## Model Card Contact
 
-[More Information Needed]
+For more information about the model or the present Model Card, you can reach out to:
+- Ricardo Muñoz Sánchez ([mailto:ricardo.munoz.sanchez@gu.se])
+- Elena Volodina ([mailto:elena.volodina@gu.se])