Update README.md

README.md

@@ -10,7 +10,7 @@ tags:
 pipeline_tag: text-classification
 ---
 
-# helizac/berturk-pair-acceptability
+# helizac/pair-acceptability-turkish
 
 This model is a fine-tuned version of `dbmdz/bert-base-turkish-cased` for classifying the acceptability of a Turkish text output given a Turkish text input.
 It was developed as part of the "Evaluation of the Acceptability of Model Outputs" (May 2025).
@@ -40,7 +40,7 @@ import torch
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
 TOKEN_KEY = "YOUR_HF_TOKEN_HERE" # Replace with your Hugging Face token or set to None
-MODEL_NAME = "helizac/berturk-pair-acceptability"
+MODEL_NAME = "helizac/pair-acceptability-turkish"
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 MAX_LENGTH = 64
@@ -113,7 +113,7 @@ print(f"Input: {input_text_2}\nOutput: {output_text_2}\nPrediction: {prediction_
 
 # Example 3: Unacceptable (grammatically poor)
 input_text_3 = "Hayalindeki meslek ne büyük."
-output_text_3 = "Olmak ben istemek büyük.
+output_text_3 = "Olmak ben istemek büyük."
 prediction_3, confidence_3 = predict_pair_acceptability(input_text_3, output_text_3, model, tokenizer, device, MAX_LENGTH)
 print(f"Input: {input_text_3}\nOutput: {output_text_3}\nPrediction: {prediction_3} (Confidence: {confidence_3:.4f})\n")
 ```
@@ -125,7 +125,7 @@ The model was fine-tuned on a dataset of approximately 460,000 Turkish input-out
 All pairs were truncated/padded to a maximum sequence length of 64 tokens for the combined input and output.
 
 ## Evaluation Results
-On a manually curated, independent Turkish test set (89 pairs evaluated due to token limits), this model (helizac/berturk-pair-acceptability) achieved an accuracy of 87%.
+On a manually curated, independent Turkish test set (89 pairs evaluated due to token limits), this model (helizac/pair-acceptability-turkish) achieved an accuracy of 87%.
 
 The stress test for this model showed: