Update README.md

README.md

@@ -10,7 +10,7 @@ license: mit
 
 # SchorbGPT-Medium
 
-This is a GPT-2 style language model trained on web data. The model uses the GPT-2 architecture and tokenizer.
+This is a medium sized language model trained on web data. The model uses the GPT-2 architecture and tokenizer.
 
 ## Model Details
 
@@ -75,7 +75,7 @@ The model achieves a word perplexity of 38.65 on WikiText, which is competitive
 
 3. Linguistic Understanding:
    - LAMBADA: 33.90% accuracy with perplexity of 36.21
-   - HellaSwag: 29.06% (Random baseline: 25%)
+   - HellaSwag: 31.26% (Random baseline: 25%)
    - Performance indicates basic linguistic and contextual understanding
    - Typical range for non-fine-tuned models of this scale