Add paper link, project page and clarify training procedure

README.md

@@ -1,18 +1,17 @@
-
 ---
-license: apache-2.0
 datasets:
 - oscar-corpus/OSCAR-2109
 language:
 - en
 - nl
-pipeline_tag: text-generation
 library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
 ---
 
 # B-GPT_en_nl_sequential
 
-This is a bilingual GPT-2 style model. For the first half of training, this model was trained only on English data. In the second half of training, the model was trained on only Dutch data. At the end of training, 50% of training data seen by the model is English and 50% is Dutch. The tokenizer was trained on the same overall proportions of data as the language model at the final step. 
+This is a bilingual GPT-2 style model trained using a sequential approach. The first half of training used only English data, followed by the second half using only Dutch data. The final model has been exposed to roughly equal proportions of English and Dutch text (50% each). The tokenizer was also trained on a similar proportion of English and Dutch data.
 
 ## Model details:
 
@@ -38,31 +37,28 @@ Load the model:
 
 Note: if you do not specify a revision, it will load the final checkpoint of the model. See above for the list of checkpoints. The checkpoint step is the name of the revision.
 
-```
-from transformers import AutoTokenizer, AutoModel
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
 tokenizer = AutoTokenizer.from_pretrained("catherinearnett/B-GPT_en_nl_sequential")
-model = AutoModel.from_pretrained("catherinearnett/B-GPT_en_nl_sequential", revision = "128000")
-
-
-````
+model = AutoModelForCausalLM.from_pretrained("catherinearnett/B-GPT_en_nl_sequential", revision = "128000")
+```
 
 Text Generation:
 
-```
+```python
 from transformers import pipeline
 
 pipe = pipeline("text-generation", model="catherinearnett/B-GPT_en_nl_sequential")
     
-pipe("I am a")
-
+print(pipe("I am a", max_length=20)[0]["generated_text"])
 ```
 
 ## Citation
 
 If you use this model, please cite:
 
-```
+```bibtex
 @article{arnett2025acquisition,
   author = {Catherine Arnett and Tyler A. Chang and James A. Michaelov and Benjamin K. Bergen},
   title = {On the Acquisition of Shared Grammatical Representations in Bilingual Language Models},
@@ -71,3 +67,7 @@ If you use this model, please cite:
   url = {https://arxiv.org/abs/2503.03962}
 }
 ```
+
+This model was presented in the paper [On the Acquisition of Shared Grammatical Representations in Bilingual Language Models](https://arxiv.org/abs/2503.03962).
+
+Project Page: https://osf.io/5cw2e/