Upload README.md with huggingface_hub

README.md

@@ -57,7 +57,7 @@ Verified on GPU with PyTorch 2.7 / CUDA 11.8.
 
 ## Related Models
 
-See the full [SpliceBERT collection](<COLLECTION_URL>).
+See the full [SpliceBERT collection](https://huggingface.co/collections/Taykhoom/splicebert-6a20b72e9bec05b79ce009aa).
 
 | Model | Context | Training data | Notes |
 |---|---|---|---|
@@ -69,17 +69,15 @@ See the full [SpliceBERT collection](<COLLECTION_URL>).
 
 ```python
 import torch
-from transformers import BertTokenizer, BertModel
+from transformers import AutoTokenizer, AutoModel
 
-tokenizer = BertTokenizer.from_pretrained("Taykhoom/SpliceBERT-510nt")
-model = BertModel.from_pretrained("Taykhoom/SpliceBERT-510nt")
+tokenizer = AutoTokenizer.from_pretrained("Taykhoom/SpliceBERT-510nt", trust_remote_code=True)
+model = AutoModel.from_pretrained("Taykhoom/SpliceBERT-510nt", trust_remote_code=True)
 model.eval()
 
-# Sequence must be exactly 510 nt; U->T conversion; space-separated
+# Sequence must be exactly 510 nt; tokenizer handles U->T automatically
 seq = ("ATCGATCG" * 64)[:510]  # exactly 510 nt
-seq_spaced = " ".join(list(seq.upper().replace("U", "T")))
-
-enc = tokenizer(seq_spaced, return_tensors="pt")
+enc = tokenizer(seq, return_tensors="pt")
 
 with torch.no_grad():
     out = model(**enc, output_hidden_states=True)