Update README.md

README.md

@@ -77,13 +77,6 @@ MathLlama 3.2 is a fine-tuned version of Meta's Llama-3.2-3B-Instruct model, spe
 - **Context Length**: 128k tokens
 - **Architecture**: Transformer-based with optimized attention mechanisms
 
-## Performance Benchmarks
-
-| Task | Metric | Base Model | MathLlama 3.2 | Improvement |
-|------|--------|------------|---------------|-------------|
-| Abstract Algebra (MMLU) | Accuracy | 45.2% | 55.2% | **+10.0%** |
-| Mathematical Reasoning | Problem Solving | Baseline | Enhanced | Significant |
-
 ## Usage
 
 ### Basic Usage
@@ -153,18 +146,4 @@ This model is designed to enhance mathematical education and research. Users sho
 - Verify critical mathematical results independently
 - Use the model as a tool to augment, not replace, human mathematical reasoning
 - Be aware of potential biases in synthetic training data
-
-## Citation
-
-If you use MathLlama 3.2 in your research or applications, please cite:
-
-```
-@misc{mathllama2024,
-  title={MathLlama 3.2: Enhanced Mathematical Reasoning with Synthetic CoT Data},
-  author={Your Name},
-  year={2024},
-  note={Fine-tuned Llama-3.2 model for advanced mathematical reasoning}
-}
-```
-
 ---