Update README.md

README.md

@@ -29,7 +29,7 @@ MutBERT-Multi is a transformer-based genome foundation model trained on 100 mult
 ```python
 from transformers import AutoTokenizer, AutoModel
 
-model_name = "JadenLong/MutBERT-Multi"
+model_name = "CompBioDSA/MutBERT-Multi"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModel.from_pretrained(model_name, trust_remote_code=True)
 ```
@@ -44,7 +44,7 @@ import torch.nn.functional as F
 
 from transformers import AutoTokenizer, AutoModel
 
-model_name = "JadenLong/MutBERT-Multi"
+model_name = "CompBioDSA/MutBERT-Multi"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModel.from_pretrained(model_name, trust_remote_code=True)
 
@@ -70,7 +70,7 @@ print(embedding_max.shape) # expect to be 768
 ```python
 from transformers import AutoModelForSequenceClassification
 
-model_name = "JadenLong/MutBERT-Multi"
+model_name = "CompBioDSA/MutBERT-Multi"
 model = AutoModelForSequenceClassification.from_pretrained(model_name, trust_remote_code=True, num_labels=2)
 ```
 
@@ -81,7 +81,7 @@ Allowed types for RoPE scaling are: `linear` and `dynamic`. To extend the model'
 If you want to scale your model context by 2x:
 
 ```python
-model_name = "JadenLong/MutBERT-Multi"
+model_name = "CompBioDSA/MutBERT-Multi"
 model = AutoModel.from_pretrained(model_name,
                                   trust_remote_code=True,
                                   rope_scaling={'type': 'dynamic','factor': 2.0}