updating model peptriever_2023-06-23T16:07:24.508460

README.md

@@ -4,12 +4,19 @@ license: mit
 datasets:
 - ronig/protein_binding_sequences
 ---
-# Protein BiEncoder Bert Model
+## Peptriever BiEncoder for Protein-Peptide Binding
+The model and training process is outlined in [this application note](). Training code can be found [here](https://github.com/RoniGurvich/Peptriever). 
+
+For more details see the [application page](https://peptriever.app) 
+
+## Usage
 
-Usage
 ```python
+import torch
+from transformers import AutoModel, AutoTokenizer
+
 tokenizer = AutoTokenizer.from_pretrained("ronig/protein_biencoder")
-model = BiEncoder.from_pretrained("ronig/protein_biencoder")
+model = AutoModel.from_pretrained("ronig/protein_biencoder", trust_remote_code=True)
 model.eval()
 
 peptide_sequence = "AAA"
@@ -24,4 +31,5 @@ with torch.no_grad():
 print("distance: ", torch.norm(peptide_output - protein_output, p=2))
 ```
 
+## Version
 Model checkpint: `peptriever_2023-06-23T16:07:24.508460`