Update README.md

README.md

@@ -1,3 +1,117 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+language:
+- ru
+base_model:
+- ai-forever/ruBert-large
+---
+# Model Card for Model ID
+
+Regression model which predicts difficulty score for an input text. Predicted scores can be mapped to CEFT levels. 
+
+
+## Model Details
+
+Frozen BERT-large layers with a regressor on top. Trained on a mix of manually annotated datasets (more details on data will follow).
+
+
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+```
+class CustomModel(BertPreTrainedModel):
+    def __init__(self, config, load_path=None, use_auth_token: str = None,):
+        super().__init__(config)
+        self.bert = BertModel(config)
+        self.pre_classifier = nn.Linear(config.hidden_size, 128)
+        self.dropout = nn.Dropout(0.2)
+        self.classifier = nn.Linear(128, 1)
+
+        # Apply Xavier initialization
+        nn.init.xavier_uniform_(self.pre_classifier.weight)
+        nn.init.xavier_uniform_(self.classifier.weight)
+        if self.pre_classifier.bias is not None:
+            nn.init.constant_(self.pre_classifier.bias, 0)
+        if self.classifier.bias is not None:
+            nn.init.constant_(self.classifier.bias, 0)
+
+    
+    def forward(
+            self,
+            input_ids,
+            labels=None,
+            attention_mask=None,
+            token_type_ids=None,
+            position_ids=None,
+    ):
+        outputs = self.bert(
+            input_ids,
+            attention_mask=attention_mask,
+            token_type_ids=token_type_ids,
+            position_ids=position_ids,
+        )
+
+
+        pooled_output = outputs[0][:, 0]
+        pooled_output = self.pre_classifier(pooled_output)
+        pooled_output = nn.ReLU()(pooled_output)  
+        pooled_output = self.dropout(pooled_output)  
+        logits = self.classifier(pooled_output) 
+
+        if labels is not None:
+            loss_fn = nn.MSELoss()
+            loss = loss_fn(logits.view(-1), labels.view(-1))
+            return loss, logits
+        else:
+            return None, logits
+
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
+config.num_labels = 1
+
+model = CustomModel(config)
+model.load_state_dict(torch.load(f'{model_path}/pytorch_model.bin'))
+
+inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
+inputs = {key: value.to(device) for key, value in inputs.items()}
+        
+with torch.no_grad():
+  _, logits = model(input_ids=inputs["input_ids"], attention_mask=inputs["attention_mask"], token_type_ids=inputs["token_type_ids"])
+
+```
+
+To map to CEFR, use: 
+```
+reg2cl2 = {'1.0': 'A1', '1.5': 'A12', '2.0': 'A2', '2.5': 'A2', '3.0': 'B1', '3.5': 'B12', '4.0': 'B2', '4.5': 'B2', '5.0': 'C1', '5.5': 'C12', '6.0': 'C2', '0.0': 'A1'}
+print("Predicted output (logits):", logits.item(), reg2cl2[str(float(round(logits.item())))])
+```
+
+
+
+## Training Details
+
+
+#### Training Hyperparameters
+
++ learning_rate: 3e-4
++ num_train_epochs: 15.0
++ batch_size: 32
++ weight_decay: 0.1
++ adam_beta1: 0.9
++ adam_beta2: 0.99
++ adam_epsilon: 1e-8
++ max_grad_norm:  1.0
++ fp16: True
+
+
+## Evaluation
+
+
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+