Update README.md

README.md

@@ -6,7 +6,6 @@
 
 **Dataset:** bitext/Bitext-customer-support-llm-chatbot-training-dataset
 
-**Quantization:** Applied FP16 for optimized inference
 
 **Training Device:** CUDA (GPU)
 
@@ -108,13 +107,6 @@ Expected Output:
 Issue: How do I cancel my order?
 Resolution: Log into the portal and cancel it there.
 ```
-# Quantization & Optimization
-Quantization: Applied FP16 using PyTorch’s .half() post-training for faster inference and reduced model size (~279MB from ~558MB).
-Optimization: Trained with mixed precision (FP16) on CUDA, further quantized for deployment efficiency.
-Usage
-Input: Text representing a customer support issue (e.g., "Customer: My payment isn’t going through, help!")
-
-Output: Text providing an actionable resolution (e.g., "Check your card details and try again.")
 
 # Limitations
 Model may struggle with issues requiring specific resolutions not well-represented in the training data (e.g., time-related queries like "When can I call support?").
@@ -122,4 +114,3 @@ Resolution extraction relied on heuristics, potentially missing nuanced answers
 # Future Improvements
 Refine resolution extraction with more advanced NLP techniques or manual curation.
 Fine-tune on additional customer support datasets for broader coverage.
-Evaluate with formal metrics (e.g., ROUGE) for quantitative performance.