Update README.md

README.md

@@ -8,7 +8,7 @@ language:
 metrics:
 - accuracy
 base_model:
-- microsoft/deberta-large
+- microsoft/deberta-v3-large
 pipeline_tag: token-classification
 ---
 
@@ -22,12 +22,12 @@ pipeline_tag: token-classification
 
 <!-- Provide a longer summary of what this model is. -->
 
-This model is a grammar error correction (GEC) system fine-tuned from the `microsoft/deberta-large` model, designed to detect and correct grammatical errors in English text. The model focuses on common grammatical mistakes such as verb tense, noun inflection, adjective usage, and more. It is particularly useful for language learners or applications requiring enhanced grammatical precision.
+This model is a grammar error correction (GEC) system fine-tuned from the `microsoft/deberta-v3-large` model, designed to detect and correct grammatical errors in English text. The model focuses on common grammatical mistakes such as verb tense, noun inflection, adjective usage, and more. It is particularly useful for language learners or applications requiring enhanced grammatical precision.
 
 - **Model type:** Token classification with sequence-to-sequence correction
 - **Language(s) (NLP):** English
 - **License:** [More Information Needed]
-- **Finetuned from model [optional]:** `microsoft/deberta-large`
+- **Finetuned from model [optional]:** `microsoft/deberta-v3-large`
 
 
 ## Uses
@@ -79,9 +79,9 @@ from torch import nn
 from torch.nn import CrossEntropyLoss
 from transformers import AutoConfig, AutoTokenizer
 from transformers.file_utils import ModelOutput
-from transformers.models.deberta.modeling_deberta import (
-    DebertaModel,
-    DebertaPreTrainedModel,
+from transformers.models.deberta_v2.modeling_deberta_v2 import (
+    DebertaV2Model,
+    DebertaV2PreTrainedModel,
 )
 
 
@@ -103,7 +103,7 @@ class XGECToROutput(ModelOutput):
     attentions: Optional[Tuple[torch.FloatTensor]] = None
 
 
-class XGECToRDeberta(DebertaPreTrainedModel):
+class XGECToRDebertaV3(DebertaV2PreTrainedModel):
     """
     This class overrides the GECToR model to include an error detection head in addition to the token classification head.
     """
@@ -116,7 +116,7 @@ class XGECToRDeberta(DebertaPreTrainedModel):
         self.num_labels = config.num_labels
         self.unk_tag_idx = config.label2id.get("@@UNKNOWN@@", None)
 
-        self.deberta = DebertaModel(config)
+        self.deberta = DebertaV2Model(config)
 
         self.classifier = nn.Linear(config.hidden_size, config.num_labels)
 
@@ -249,5 +249,5 @@ The primary evaluation metric used was F0.5, measuring the model's ability to id
 
 ### Results
 
-F0.5 = 73.05
+F0.5 = 74.61