Update README.md

README.md

@@ -32,11 +32,12 @@ This model is a fine-tuned version of ModernBERT-base designed to evaluate the *
 
 The model uses an additive 5-point rating system:
 
-- **1 point**: Somewhat readable but contains significant clarity or coherence issues, complex vocabulary, or numerous errors
-- **2 points**: Generally clear and coherent with occasional grammar, spelling errors, or convoluted structures
-- **3 points**: Clear and coherent for the most part, using appropriate vocabulary with minor grammar/spelling issues
-- **4 points**: Very clear and coherent with very few or no errors, proper punctuation and easy-to-follow structures
-- **5 points**: Outstanding clarity and coherence, effective communication with minimal errors that don't interfere with understanding
+- **0**: absolute not readable
+- **1**: Somewhat readable but contains significant clarity or coherence issues, complex vocabulary, or numerous errors
+- **2**: Generally clear and coherent with occasional grammar, spelling errors, or convoluted structures
+- **3**: Clear and coherent for the most part, using appropriate vocabulary with minor grammar/spelling issues
+- **4**: Very clear and coherent with very few or no errors, proper punctuation and easy-to-follow structures
+- **5**: Outstanding clarity and coherence, effective communication with minimal errors that don't interfere with understanding
 
 ## Usage
 
@@ -56,7 +57,7 @@ text = "The weather today is sunny and warm. It's a perfect day for outdoor acti
 inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=4096)
 with torch.no_grad():
     outputs = model(**inputs)
-    score = outputs.logits.squeeze().item()
+    score = outputs.logits.squeeze().argmax(dim=0)
 
 print(f"Readability Score: {score:.2f}")
 ```