Update README.md

README.md

@@ -20,9 +20,9 @@ base_model:
 
 # ru-summary-quality-metric
 
-This model is a fine-tuned version of [`ai-forever/ruT5-large`](https://huggingface.co/ai-forever/ruT5-large), trained for binary quality assessment of summaries for "text - summary" pairs in Russian.
+This model is a fine-tuned version of [`ai-forever/ruT5-large`](https://huggingface.co/ai-forever/ruT5-large), was trained for binary quality assessment of Russian summaries when paired with their original texts.
 
-**Important:** Model uses a non-standard approach, adapting a Seq2Seq model for a binary classification task. It was trained to predict a specific token as the target sequence. This approach directly follows the methodology used by authors of original SEAHORSE paper.
+**Important:** model uses a non-standard approach, adapting a Seq2Seq model for a binary classification task. It was trained to predict a specific token as the target sequence. This approach directly follows the methodology used by the authors of the original SEAHORSE paper.
 
 ## Data and Training Metric
 
@@ -30,12 +30,12 @@ The model was fine-tuned on [SEAHORSE](https://huggingface.co/datasets/hgissbkh/
 
 This specific model focuses on Q6 Conciseness metric. According to SEAHORSE paper authors, Q6 is considered one of the most high-level and challenging quality metrics.
 
-* **Training Data:** `ru` and `en` subsets training split, filtered for `conciseness` labels.
+* **Training Data:** `ru` and `en` subsets of training split, filtered for `conciseness` labels.
 * **Evaluation Data:** only `ru` subset of validation and test splits.
 
 ## Evaluation Results
 
-|Test Set|Pearson Correlation|ROC AUC|
+|Test set|Pearson Correlation|ROC AUC|
 |-|-|-|
 |All|0.479|0.792|
 |≥ 20 summary words |0.459|0.781|
@@ -85,8 +85,7 @@ def predict_conciseness_score(text, summary, tokenizer, model, device, zero_toke
         logit_0 = first_token_logits[zero_token_id]
         logit_1 = first_token_logits[one_token_id]
 
-        score_diff = logit_1 - logit_0
-        probability_of_one = torch.sigmoid(torch.tensor(score_diff)).item()
+        probability_of_one = torch.sigmoid(logit_1 - logit_0).item()
 
     return probability_of_one
 ```