Update README to include transformers version requirement

README.md

@@ -121,6 +121,12 @@ model-index:
 ModChemBERT is a ModernBERT-based chemical language model (CLM), trained on SMILES strings for masked language modeling (MLM) and downstream molecular property prediction (classification & regression).
 
 ## Usage
+Install the `transformers` library starting from v4.56.1:
+
+```bash
+pip install -U transformers>=4.56.1
+```
+
 ### Load Model
 ```python
 from transformers import AutoModelForMaskedLM, AutoTokenizer

config.json

@@ -1,12 +1,14 @@
 {
   "architectures": [
-    "ModChemBertForMaskedLM"
+    "ModChemBertForMaskedLM",
+    "ModChemBertForSequenceClassification"
   ],
   "attention_bias": false,
   "attention_dropout": 0.1,
   "auto_map": {
     "AutoConfig": "configuration_modchembert.ModChemBertConfig",
-    "AutoModelForMaskedLM": "modeling_modchembert.ModChemBertForMaskedLM"
+    "AutoModelForMaskedLM": "modeling_modchembert.ModChemBertForMaskedLM",
+    "AutoModelForSequenceClassification": "modeling_modchembert.ModChemBertForSequenceClassification"
   },
   "bos_token_id": 0,
   "classifier_activation": "gelu",