Update README.md

README.md

@@ -1,3 +1,30 @@
----
-license: mit
----
+---
+license: mit
+---
+
+## Constant-650M
+Constant-650M is an antibody language model that uses an [ESM-2](https://www.science.org/doi/10.1126/science.ade2574) architecture. 
+It was pre-trained on unpaired and paired sequences from the [OAS](https://opig.stats.ox.ac.uk/webapps/oas/), using the constant approach described in our [preprint on biorxiv](https://doi.org/10.1101/2025.02.27.640641). 
+Datasets used for pre-training are avaliable on [Zenodo](https://doi.org/10.5281/zenodo.14661302) and code is avaliable on [GitHub](https://github.com/brineylab/curriculum-paper).  
+
+### Use
+Load the model and tokenizer as follows:
+```python
+from transformers import EsmTokenizer, EsmForMaskedLM
+
+model = EsmForMaskedLM.from_pretrained("brineylab/Constant-650M")
+tokenizer = EsmTokenizer.from_pretrained("brineylab/Constant-650M")
+```
+
+The tokenizer expects inputs in the format: ["VQ..SS\<cls>EV..IK"] for paired sequences, ["VQ..SS\<cls>"] for unpaired heavy chains and ["\<cls>EV..IK"] for unpaired light chains. 
+
+The model can be finetuned for classification tasks (such as specificity and pair classification in the paper) by loading the model with a sequence classification head:
+```python
+from transformers import EsmForSequenceClassification
+
+model = EsmForSequenceClassification.from_pretrained("brineylab/Constant-650M")
+
+# freeze the base model weights prior to finetuning
+for param in model.base_model.parameters():
+    param.requires_grad = False
+```