Update README.md

README.md

@@ -20,7 +20,7 @@ pipeline_tag: text-classification
 <!-- ![deck](deck.png){: width="200px"} -->
 <img src="deck.png" width="800">
 
-This is derivative version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base). <br>
+This is a derivative version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base). <br>
 We fine-tuned ModernBERT-base to detect vulnerability in C/C++ Code. <br>
 The actual version has an accuracy of 82% <br>
 
@@ -28,7 +28,9 @@ The actual version has an accuracy of 82% <br>
 
 ### Model Description
 
-ThreatDetect-C-Cpp can be used as a code classifier. Instead of binary classification ("safe", "unsafe"), it classify the input code into 7 labels: 'safe' (no vulnerability detected) and six other CWE weaknesses:
+ThreatDetect-C-Cpp can be used as a code classifier. <br>
+Instead of binary classification ("safe", "unsafe"), The model classifies the input code into 7 labels: 'safe' (no vulnerability detected) and six other CWE weaknesses:
+
 | Label  | Description                                         |
 |---------|-------------------------------------------------------|
 | CWE-119 | Improper Restriction of Operations within the Bounds of a Memory Buffer |
@@ -105,7 +107,7 @@ The model was trained using LoRA applied to Q and V matrices.
 
 ## Evaluation
 
-ThreatDetect-C-Cpp reaches an accruacy of 82%.
+ThreatDetect-C-Cpp reaches an accruacy of 82% on the eval set.