Fix README.md again

README.md

@@ -338,43 +338,23 @@ uv sync
 ```
 
 </details>
-"""
-
-    script_section = f"""<details>
-  <summary><strong>Quantization Script</strong></summary>
-
-Below is the exact `quantize.py` script used to generate this model:
-
-```python
-{script_content}
-```
-
-</details>
-"""
-
-    performance_section = f"""<details>
   <summary><strong>Quantization Performance</strong></summary>
 
 **Average perplexity (PPL) on wikitext-2-raw-v1 dataset:** 7.89 on on wikitext-2-raw-v1 dataset
+<details>
 
 </details>
-"""
-
-    disclaimer_section = """<details>
   <summary><strong>Disclaimer</strong></summary>
 
-This model is for research purposes only. It may inherit limitations and biases from the original model and the quantization process. Please use responsibly and refer to the original model card for more details.
-
+  This model is for research purposes only. It may inherit limitations and biases from the original model and the quantization process. Please use responsibly and refer to the original model card for more details.
+<details>
 </details>
-"""
-
-    contact_section = """<details>
   <summary><strong>Contact</strong></summary>
 
 For any questions or support, please visit [ConfidentialMind](https://www.confidentialmind.com) or contact us directly.
 
 [![LinkedIn](https://img.shields.io/badge/LinkedIn-ConfidentialMind-blue)](https://www.linkedin.com/company/confidentialmind/)
-
+<details>
 </details>
 """
 
@@ -386,18 +366,14 @@ This model inherits the license from the original model. Please refer to the ori
 Original model card: `{source_model}`
 
 </details>
-"""
-
-    author_section = """<details>
   <summary><strong>Author</strong></summary>
 
 This model was quantized by [![LinkedIn](https://img.shields.io/badge/LinkedIn-Jaro-blue)](https://www.linkedin.com/in/jaroai/)
+<details>
 
 </details>
-"""
-
-    ack_section = """<details>
   <summary><strong>Acknowledgements</strong></summary>
+<details>
 
 Quantization performed using the GPTQModel pipeline and a big thanks to NeuralMagic for creating the calibration dataset, as well as the models original creators and/or fine-tuners.