update readme

README.md

@@ -117,7 +117,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 - **Provider:** UMass Gypsum HPC
 - **Carbon Estimate:** <1 kg CO₂ (low academic footprint)
 
-## Technical Specifications [optional]
+## Technical Specifications:
 
 ### Model Architecture and Objective
 
@@ -131,7 +131,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Glossary
 
-- **LoRA (Low-Rank Adaptation):** A parameter-efficient fine-tuning method where only small adapter matrices are trained, while the large base model remains frozen. This drastically reduces compute and storage costs.\
+- **LoRA (Low-Rank Adaptation):** A parameter-efficient fine-tuning method where only small adapter matrices are trained, while the large base model remains frozen. This drastically reduces compute and storage costs.
 - **4-bit Quantization:** A compression technique that reduces model weights from 16/32-bit floating-point numbers to 4-bit representations. This allows large models (like Saul-7B) to fit and run on smaller GPUs with minimal accuracy loss.
 - **ToS (Terms of Service) Anomaly Detection:** The task of identifying clauses in service agreements that are potentially unfair, unusual, or restrictive for consumers (e.g., sudden account termination, hidden fees).
 - **PEFT (Parameter-Efficient Fine-Tuning):** A family of methods (like LoRA) that fine-tune large models by updating only a small subset of parameters instead of the entire model.
@@ -154,7 +154,7 @@ For questions, feedback, or collaborations, please reach out:
 ### Framework Versions
 - **Transformers:** 4.51.3  
 - **PEFT:** 0.15.2  
-- **PyTorch:** 2.2.2+cu121  
+- **PyTorch:** 2.2.2 
 - **Datasets:** 2.21.0  
 
 ### Framework versions