Apply BERTose display capitalization

Files changed (5) hide show

README.md CHANGED Viewed

@@ -9,16 +9,16 @@ tags:
 - pytorch
 ---
-# Bertose Glycan Encoder
-This repository contains the Bertose checkpoint for WURCS glycan embedding inference. It is the release-facing glycan representation model used by the companion notebook.
 ## Files
-- `checkpoints/bertose_glycan_encoder.pt` - Bertose glycan encoder checkpoint.
 - `vocab/bpe_vocabulary.json` - WURCS BPE vocabulary.
-- `src/bertose_model.py` - Bertose model definition.
-- `src/bertose_layers.py` - Transformer layers used by Bertose.
 - `src/wurcs_bpe_tokenizer.py` - WURCS BPE tokenizer.
 ## Input

 - pytorch
 ---
+# BERTose Glycan Encoder
+This repository contains the BERTose checkpoint for WURCS glycan embedding inference. It is the release-facing glycan representation model used by the companion notebook.
 ## Files
+- `checkpoints/bertose_glycan_encoder.pt` - BERTose glycan encoder checkpoint.
 - `vocab/bpe_vocabulary.json` - WURCS BPE vocabulary.
+- `src/bertose_model.py` - BERTose model definition.
+- `src/bertose_layers.py` - Transformer layers used by BERTose.
 - `src/wurcs_bpe_tokenizer.py` - WURCS BPE tokenizer.
 ## Input

SHA256SUMS CHANGED Viewed

@@ -1,9 +1,9 @@
 622368f62c23e97e9137c277eaadcc93ee3901cbb420b591422bb1c2e19689a5  ./.gitattributes
-acca581727a41c8ecc6f92e45539f5a5cec3a5d5bdf9113a38e9b911e24eb766  ./README.md
 9ff260796c28e9f254d87da95592c686874d3954429d926d99afd2a8f9b6c08f  ./checkpoints/bertose_glycan_encoder.pt
-7233493ffa6eaf57fd3db9e1583ff59a831099175597d64e36e1b28aa31b4cf7  ./config.json
 6a56e6f73b8f874470ecde6e538f3f5029ae23aa6c10559817d1c2a8b59b7c0f  ./requirements.txt
-6362da8e8de0dc4d580c7d94ef6ab1dbc737da13127fc4078681ce6315180086  ./src/bertose_layers.py
-3c5b826fcf5850749f74d980eee48d0595557f3d6e2a58aa873902817eb65c64  ./src/bertose_model.py
 0bc54399362945601bcfd403441fc80968d173200dd0561f57568b2053a94839  ./src/wurcs_bpe_tokenizer.py
 6a572afdf53f1494ab96c896876b824ca7ea749777352606aa9f96bf270ceecc  ./vocab/bpe_vocabulary.json

 622368f62c23e97e9137c277eaadcc93ee3901cbb420b591422bb1c2e19689a5  ./.gitattributes
+a48dc3bc0dbe330ceddf8a9e32be9f699043c17a74956e852fb658c2ef233bc4  ./README.md
 9ff260796c28e9f254d87da95592c686874d3954429d926d99afd2a8f9b6c08f  ./checkpoints/bertose_glycan_encoder.pt
+d5854b5960b949bee17dcae3078ad15641dd24516a6c73835784518d73adf979  ./config.json
 6a56e6f73b8f874470ecde6e538f3f5029ae23aa6c10559817d1c2a8b59b7c0f  ./requirements.txt
+3587aa789041e4ee215dcaa0286847d45621e9514c0ed3efa314fb89cf40f4d7  ./src/bertose_layers.py
+773023d70be02ecf4a26b79b18b2b70ee1b39e01ec287386cb162590aaf90767  ./src/bertose_model.py
 0bc54399362945601bcfd403441fc80968d173200dd0561f57568b2053a94839  ./src/wurcs_bpe_tokenizer.py
 6a572afdf53f1494ab96c896876b824ca7ea749777352606aa9f96bf270ceecc  ./vocab/bpe_vocabulary.json

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "model_family": "Bertose",
   "release_name": "bertose-glycan-encoder",
   "checkpoint": "checkpoints/bertose_glycan_encoder.pt",
   "vocabulary": "vocab/bpe_vocabulary.json",

 {
+  "model_family": "BERTose",
   "release_name": "bertose-glycan-encoder",
   "checkpoint": "checkpoints/bertose_glycan_encoder.pt",
   "vocabulary": "vocab/bpe_vocabulary.json",

src/bertose_layers.py CHANGED Viewed

@@ -1,5 +1,5 @@
 """
-Bertose transformer layers.
 Transformer blocks adapted for WURCS glycan tokenization.
 """
@@ -10,7 +10,7 @@ import math
 class GlycanBERTConfig:
-    """Configuration for the Bertose transformer stack."""
     def __init__(
         self,
@@ -202,7 +202,7 @@ class GlycanBERTLayer(nn.Module):
 class GlycanBERT(nn.Module):
     """
-    Bertose transformer stack for masked language modeling.
     """
     def __init__(self, config: GlycanBERTConfig):

 """
+BERTose transformer layers.
 Transformer blocks adapted for WURCS glycan tokenization.
 """
 class GlycanBERTConfig:
+    """Configuration for the BERTose transformer stack."""
     def __init__(
         self,
 class GlycanBERT(nn.Module):
     """
+    BERTose transformer stack for masked language modeling.
     """
     def __init__(self, config: GlycanBERTConfig):

src/bertose_model.py CHANGED Viewed

@@ -1,5 +1,5 @@
 """
-Bertose model
 Core glycan representation model with three modalities:
 - Sequence (WURCS atomic tokenization)
@@ -148,7 +148,7 @@ def create_residue_level_mask(
 class MultimodalGlycanBERTConfig:
-    """Configuration for the Bertose model."""
     def __init__(
         self,
@@ -610,7 +610,7 @@ class CrossAttentionLayer(nn.Module):
 class MultimodalGlycanBERT(nn.Module):
     """
-    Bertose model for glycan representation learning.
     Architecture:
     1. Separate encoders for each modality (sequence, MS, 3D structure)
@@ -722,7 +722,7 @@ class MultimodalGlycanBERT(nn.Module):
         return_dict: bool = True,
     ) -> Dict[str, torch.Tensor]:
         """
-        Forward pass for Bertose.
         Args:
             seq_token_ids: (batch_size, seq_len) - Sequence token IDs
@@ -970,7 +970,7 @@ class MultimodalGlycanBERT(nn.Module):
 if __name__ == "__main__":
     # Test the model
     print("="*80)
-    print("Testing Bertose model")
     print("="*80)
     # Create config

 """
+BERTose model
 Core glycan representation model with three modalities:
 - Sequence (WURCS atomic tokenization)
 class MultimodalGlycanBERTConfig:
+    """Configuration for the BERTose model."""
     def __init__(
         self,
 class MultimodalGlycanBERT(nn.Module):
     """
+    BERTose model for glycan representation learning.
     Architecture:
     1. Separate encoders for each modality (sequence, MS, 3D structure)
         return_dict: bool = True,
     ) -> Dict[str, torch.Tensor]:
         """
+        Forward pass for BERTose.
         Args:
             seq_token_ids: (batch_size, seq_len) - Sequence token IDs
 if __name__ == "__main__":
     # Test the model
     print("="*80)
+    print("Testing BERTose model")
     print("="*80)
     # Create config