docs: update usage example

README.md

@@ -20,14 +20,47 @@ Source code and data: https://github.com/AIRI-Institute/GENA_LM
 Paper: https://www.biorxiv.org/content/10.1101/2023.06.12.544594v1
 
 ## Examples
-### How to load the model to fine-tune it on classification task
+
+### How to load pre-trained model for Masked Language Modeling
+```python
+from transformers import AutoTokenizer, AutoModel
+
+tokenizer = AutoTokenizer.from_pretrained('AIRI-Institute/gena-lm-bert-base')
+model = AutoModel.from_pretrained('AIRI-Institute/gena-lm-bert-base', trust_remote_code=True)
+
+```
+
+### How to load pre-trained model to fine-tune it on classification task
+Get model class from GENA-LM repository:
+```bash
+git clone https://github.com/AIRI-Institute/GENA_LM.git
+```
+
 ```python
-from src.gena_lm.modeling_bert import BertForSequenceClassification
+from GENA_LM.src.gena_lm.modeling_bert import BertForSequenceClassification
 from transformers import AutoTokenizer
 
 tokenizer = AutoTokenizer.from_pretrained('AIRI-Institute/gena-lm-bert-base')
 model = BertForSequenceClassification.from_pretrained('AIRI-Institute/gena-lm-bert-base')
 ```
+or you can just download [modeling_bert.py](https://github.com/AIRI-Institute/GENA_LM/tree/main/src/gena_lm) and put it close to your code.
+
+OR you can get model class from HuggingFace AutoModel:
+```python
+from transformers import AutoTokenizer, AutoModel
+model = AutoModel.from_pretrained('AIRI-Institute/gena-lm-bert-base', trust_remote_code=True)
+gena_module_name = model.__class__.__module__
+print(gena_module_name)
+import importlib
+# available class names:
+# - BertModel, BertForPreTraining, BertForMaskedLM, BertForNextSentencePrediction,
+# - BertForSequenceClassification, BertForMultipleChoice, BertForTokenClassification,
+# - BertForQuestionAnswering
+# check https://huggingface.co/docs/transformers/model_doc/bert
+cls = getattr(importlib.import_module(gena_module_name), 'BertForSequenceClassification')
+print(cls)
+model = cls.from_pretrained('AIRI-Institute/gena-lm-bert-base', num_labels=2)
+```
 
 ## Model description
 GENA-LM (`gena-lm-bert-base`) model is trained in a masked language model (MLM) fashion, following the methods proposed in the BigBird paper by masking 15% of tokens. Model config for `gena-lm-bert-base` is similar to the bert-base: