Update README.md

README.md

@@ -37,71 +37,6 @@ A flexible, adaptive classification system that allows for dynamic addition of n
 pip install adaptive-classifier
 ```
 
-## Quick Start
-
-```python
-from adaptive_classifier import AdaptiveClassifier
-
-# Initialize with any HuggingFace model
-classifier = AdaptiveClassifier("bert-base-uncased")
-
-# Add some examples
-texts = [
-    "The product works great!",
-    "Terrible experience",
-    "Neutral about this purchase"
-]
-labels = ["positive", "negative", "neutral"]
-
-classifier.add_examples(texts, labels)
-
-# Make predictions
-predictions = classifier.predict("This is amazing!")
-print(predictions)  # [('positive', 0.85), ('neutral', 0.12), ('negative', 0.03)]
-
-# Save the classifier
-classifier.save("./my_classifier")
-
-# Load it later
-loaded_classifier = AdaptiveClassifier.load("./my_classifier")
-
-# The library is also integrated with Hugging Face. So you can push and load from HF Hub.
-
-# Save to Hub
-classifier.push_to_hub("adaptive-classifier/model-name")
-
-# Load from Hub
-classifier = AdaptiveClassifier.from_pretrained("adaptive-classifier/model-name")
-```
-
-## Advanced Usage
-
-### Adding New Classes Dynamically
-
-```python
-# Add a completely new class
-new_texts = [
-    "Error code 404 appeared",
-    "System crashed after update"
-]
-new_labels = ["technical"] * 2
-
-classifier.add_examples(new_texts, new_labels)
-```
-
-### Continuous Learning
-
-```python
-# Add more examples to existing classes
-more_examples = [
-    "Best purchase ever!",
-    "Highly recommend this"
-]
-more_labels = ["positive"] * 2
-
-classifier.add_examples(more_examples, more_labels)
-```
-
 ## How It Works
 
 The system combines three key components:
@@ -112,45 +47,6 @@ The system combines three key components:
 
 3. **Adaptive Neural Layer**: Learns refined decision boundaries through continuous training
 
-## Requirements
-
-- Python ≥ 3.8
-- PyTorch ≥ 2.0
-- transformers ≥ 4.30.0
-- safetensors ≥ 0.3.1
-- faiss-cpu ≥ 1.7.4 (or faiss-gpu for GPU support)
-
-## Benefits of Adaptive Classification in LLM Routing
-
-We evaluate the effectiveness of adaptive classification in optimizing LLM routing decisions. Using the arena-hard-auto-v0.1 dataset with 500 queries, we compared routing performance with and without adaptation while maintaining consistent overall success rates.
-
-### Key Results
-
-| Metric | Without Adaptation | With Adaptation | Impact |
-|--------|-------------------|-----------------|---------|
-| High Model Routes | 113 (22.6%) | 98 (19.6%) | 0.87x |
-| Low Model Routes | 387 (77.4%) | 402 (80.4%) | 1.04x |
-| High Model Success Rate | 40.71% | 29.59% | 0.73x |
-| Low Model Success Rate | 16.54% | 20.15% | 1.22x |
-| Overall Success Rate | 22.00% | 22.00% | 1.00x |
-| Cost Savings* | 25.60% | 32.40% | 1.27x |
-
-*Cost savings calculation assumes high-cost model is 2x the cost of low-cost model
-
-### Analysis
-
-The results highlight several key benefits of adaptive classification:
-
-1. **Improved Cost Efficiency**: While maintaining the same overall success rate (22%), the adaptive classifier achieved 32.40% cost savings compared to 25.60% without adaptation - a relative improvement of 1.27x in cost efficiency.
-
-2. **Better Resource Utilization**: The adaptive system routed more queries to the low-cost model (402 vs 387) while reducing high-cost model usage (98 vs 113), demonstrating better resource allocation.
-
-3. **Learning from Experience**: Through adaptation, the system improved the success rate of low-model routes from 16.54% to 20.15% (1.22x increase), showing effective learning from successful cases.
-
-4. **ROI on Adaptation**: The system adapted to 110 new examples during evaluation, leading to a 6.80% improvement in cost savings while maintaining quality - demonstrating significant return on the adaptation investment.
-
-This real-world evaluation demonstrates that adaptive classification can significantly improve cost efficiency in LLM routing without compromising overall performance.
-
 ## References
 
 - [RouteLLM: Learning to Route LLMs with Preference Data](https://arxiv.org/abs/2406.18665)