Update README.md

README.md

@@ -19,7 +19,7 @@ The model is trained on contexts **up to 2048 tokens** in length, but can be use
 
 ## Usage
 
-**Important**: To load the model correctly, you must enable dowloading code from the model's repository: `trust_remote_code=True`, this will download the **modeling_rope_bert.py** script and load the weights into the correct architecture.
+**Important**: 4.37.2 and higher is the recommended version of `transformers`. To load the model correctly, you must enable dowloading code from the model's repository: `trust_remote_code=True`, this will download the **modeling_rope_bert.py** script and load the weights into the correct architecture.
 Otherwise, you can download this script manually and use classes from it directly to load the model.
 
 ### Basic usage (no efficient attention)
@@ -27,7 +27,7 @@ Otherwise, you can download this script manually and use classes from it directl
 ```python
 model_name = 'Tochka-AI/ruRoPEBert-classic-base-2k'
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModel.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation='eager')
 ```
 
 ### With SDPA (efficient attention)