Finalize Bertose glycan encoder release names

README.md

@@ -9,28 +9,28 @@ tags:
 - pytorch
 ---
 
-# Bertose V5B1 Glycan Encoder
+# Bertose Glycan Encoder
 
-Draft private release for Bertose glycan embedding inference.
-
-This repository contains the leakage-proof Bertose V5B1 checkpoint used for WURCS glycan embeddings. It is intended for inference through the companion cloud notebook.
+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_v5b_excluded.pt` - Bertose V5B1 checkpoint for glycan embeddings.
+- `checkpoints/bertose_glycan_encoder.pt` - Bertose glycan encoder checkpoint.
 - `vocab/bpe_vocabulary.json` - WURCS BPE vocabulary.
-- `src/multimodal_glycan_bert_v3.py` - model definition.
-- `src/glycan_bert.py` - base BERT layers used by the multimodal model.
+- `src/bertose_model.py` - Bertose model definition.
+- `src/bertose_layers.py` - Transformer layers used by Bertose.
 - `src/wurcs_bpe_tokenizer.py` - WURCS BPE tokenizer.
 
-## Expected Input
+## Input
 
-Single glycan or batch CSV with WURCS strings.
+Provide one WURCS glycan string or a CSV batch with a WURCS column. The notebook examples use `wurcs` as the column name.
 
 ## Output
 
 Dense glycan embeddings. The companion notebook defaults to `[CLS]` pooling and also supports mean pooling over valid glycan tokens.
 
-## Draft Notes
+## Notes
+
+This repository does not perform IUPAC-condensed to WURCS conversion. For now, provide WURCS directly.
 
-This model card is intentionally minimal until the final release license, citation, and manuscript wording are locked.
+The final license and citation text should be set before public release.

SHA256SUMS

@@ -1,31 +1,9 @@
-684888c0ebb17f374298b65ee2807526c066094c701bcc7ebbe1c1095f494fc1  ./.cache/huggingface/.gitignore
-e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855  ./.cache/huggingface/upload/.gitattributes.lock
-4f977599262d1c1dfa55f309216144478f7afa722e1728f2aa1a9b80f9108ff9  ./.cache/huggingface/upload/.gitattributes.metadata
-e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855  ./.cache/huggingface/upload/README.md.lock
-eb1e822610f91fafddda84f20a2d32b4cdedf1a6cfe0e218ac87cf487cd7ecbc  ./.cache/huggingface/upload/README.md.metadata
-e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855  ./.cache/huggingface/upload/SHA256SUMS.lock
-08e938d1f7308ad98a9f2ae03b0efed2d8037248b2c3b85831a17f2fc27dbfeb  ./.cache/huggingface/upload/SHA256SUMS.metadata
-e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855  ./.cache/huggingface/upload/checkpoints/bertose_v5b_excluded.pt.lock
-d9026e0f48c8644ce51f25966cb0508a41c73969758eaa523a17dbebe3198c07  ./.cache/huggingface/upload/checkpoints/bertose_v5b_excluded.pt.metadata
-e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855  ./.cache/huggingface/upload/config.json.lock
-95eee4589c49a337c15b2f1309655e780f8d4a979765baa4b98a820d4a28ffca  ./.cache/huggingface/upload/config.json.metadata
-e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855  ./.cache/huggingface/upload/requirements.txt.lock
-ead93b0a87bf2a70c99da445f90a9eee6de5da42788acbf8d469575d2d0dd75f  ./.cache/huggingface/upload/requirements.txt.metadata
-e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855  ./.cache/huggingface/upload/src/multimodal_glycan_bert_v3.py.lock
-2c560629b83d39c59e004cdb2d2ca4b375440860f75624378974504f30c8cfe1  ./.cache/huggingface/upload/src/multimodal_glycan_bert_v3.py.metadata
-e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855  ./.cache/huggingface/upload/src/wurcs_bpe_tokenizer.py.lock
-4034d7d05d0c8b83ddea008e2b718fc6603497c03e767eae7818727bfb906d2a  ./.cache/huggingface/upload/src/wurcs_bpe_tokenizer.py.metadata
-e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855  ./.cache/huggingface/upload/vocab/bpe_vocabulary.json.lock
-a36b656101e757be53780150c039df53ab5b10a2946c2df3e3a8120669d7ed43  ./.cache/huggingface/upload/vocab/bpe_vocabulary.json.metadata
 622368f62c23e97e9137c277eaadcc93ee3901cbb420b591422bb1c2e19689a5  ./.gitattributes
-5db8aaf92c4b2654eb7e1a83efaf5e0fba8a279b9c56485331febceba67d905a  ./README.md
-9ff260796c28e9f254d87da95592c686874d3954429d926d99afd2a8f9b6c08f  ./checkpoints/bertose_v5b_excluded.pt
-dd367de5dd3528e0df977984824f8ec79ad736de55877eaeb9af938fc0c2b319  ./config.json
+acca581727a41c8ecc6f92e45539f5a5cec3a5d5bdf9113a38e9b911e24eb766  ./README.md
+9ff260796c28e9f254d87da95592c686874d3954429d926d99afd2a8f9b6c08f  ./checkpoints/bertose_glycan_encoder.pt
+7233493ffa6eaf57fd3db9e1583ff59a831099175597d64e36e1b28aa31b4cf7  ./config.json
 6a56e6f73b8f874470ecde6e538f3f5029ae23aa6c10559817d1c2a8b59b7c0f  ./requirements.txt
-49026d4d29b44e3f65d57a6587d0f9567b56eee263b45713c76e5e758f7b984d  ./src/__pycache__/glycan_bert.cpython-312.pyc
-ffdebb20e6d13f35e842f06286d40429304995dd8fbad90d43213cf84fd4517e  ./src/__pycache__/multimodal_glycan_bert_v3.cpython-312.pyc
-09d284eb0e13f05d3770449523c0079e4ced2f8dd44d741ce05c39571fbc5022  ./src/__pycache__/wurcs_bpe_tokenizer.cpython-312.pyc
-b69f14c9976951325e3a0a4e8107a16126e67d410e966650f513f1f538a732bb  ./src/glycan_bert.py
-0d9ce16bf90242f38621d64cd974ea5679bff4c2013bea8d7bffe1b8dd120794  ./src/multimodal_glycan_bert_v3.py
+b69f14c9976951325e3a0a4e8107a16126e67d410e966650f513f1f538a732bb  ./src/bertose_layers.py
+f247a6c09132a61cb649acfe022b269b5b94c37a5069fcb62045f3340b96b191  ./src/bertose_model.py
 0bc54399362945601bcfd403441fc80968d173200dd0561f57568b2053a94839  ./src/wurcs_bpe_tokenizer.py
 6a572afdf53f1494ab96c896876b824ca7ea749777352606aa9f96bf270ceecc  ./vocab/bpe_vocabulary.json

config.json

@@ -1,7 +1,7 @@
 {
   "model_family": "Bertose",
-  "release_name": "bertose-v5b1-glycan-encoder",
-  "checkpoint": "checkpoints/bertose_v5b_excluded.pt",
+  "release_name": "bertose-glycan-encoder",
+  "checkpoint": "checkpoints/bertose_glycan_encoder.pt",
   "vocabulary": "vocab/bpe_vocabulary.json",
   "embedding_dim": 768,
   "max_glycan_length": 256,

src/{multimodal_glycan_bert_v3.py → bertose_model.py}

@@ -15,9 +15,9 @@ from typing import Dict, Optional, Tuple
 import math
 
 try:
-    from .glycan_bert import GlycanBERTConfig, GlycanBERTEmbeddings, GlycanBERTLayer
+    from .bertose_layers import GlycanBERTConfig, GlycanBERTEmbeddings, GlycanBERTLayer
 except ImportError:
-    from glycan_bert import GlycanBERTConfig, GlycanBERTEmbeddings, GlycanBERTLayer
+    from bertose_layers import GlycanBERTConfig, GlycanBERTEmbeddings, GlycanBERTLayer
 
 
 class ConvGlycanBERTEmbeddings(nn.Module):