Fixed README

README.md

@@ -11,14 +11,11 @@ Face .safetensors format for secure and efficient model loading.
 
 -   **Base Model**: TinyLlama 1.1B
 
--   **Fine-Tuning Dataset**: Custom Geometry CoT dataset, including
-    > 2D/3D shapes, trigonometry, and coordinate geometry problems
+-   **Fine-Tuning Dataset**: Custom Geometry CoT dataset consisting of coordinate geometry problems and geometrical construction instruction
 
--   **Model Format**: .safetensors for secure and efficient weight
-    > storage
+-   **Model Format**: .safetensors for secure and efficient weight storage
 
--   **Intended Use**: Generating geometry functions for educational
-    > tools, CAD software, game development, or computational geometry
+-   **Intended Use**: Generating geometry functions for educational tools.
 
 -   **License**: MIT
 
@@ -26,11 +23,9 @@ Face .safetensors format for secure and efficient model loading.
 
 ## **Important Note:**
 
--   Use the system_prompt.txt for the System Prompt, this provides the
-    > accurate results.
+-   Use the system_prompt.txt for the System Prompt, this provides the accurate results.
 
--   You can extract and edit the system prompt. I hope to add new
-    > functions later.
+-   You can extract and edit the system prompt. I hope to add new functions later.
 
 ## **Capabilities**
 
@@ -45,17 +40,13 @@ volume, distance, and intersection calculations.
 
 -   **Architecture**: Transformer-based, inherited from TinyLlama 1.1B
 
--   **Fine-Tuning Details**: Trained on a dataset of geometry problems
-    > with step-by-step solutions
+-   **Fine-Tuning Details**: Trained on a dataset of geometry problems with step-by-step solutions
 
--   **Output Format**: Python code or pseudocode compatible with
-    > geometry engine APIs
+-   **Output Format**: Python code or pseudocode compatible with geometry engine APIs
 
--   **Performance**: Improved accuracy on geometry tasks compared to the
-    > base TinyLlama model, with low latency
+-   **Performance**: Improved accuracy on geometry tasks compared to the base TinyLlama model, with low latency
 
--   **Model Storage**: Uses .safetensors for secure and efficient
-    > loading with Hugging Face\'s safetensors library
+-   **Model Storage**: Uses .safetensors for secure and efficient loading with Hugging Face\'s safetensors library
 
 ## **Usage**
 
@@ -89,11 +80,9 @@ pip install safetensors transformers
 
 ## **Training Details**
 
--   **Dataset**: Custom Geometry CoT dataset with 10,000 geometry
-    > problems and solutions
+-   **Dataset**: Custom Geometry CoT dataset with 10,000 geometry problems and solutions
 
--   **Training Procedure**: Fine-tuned for 3 epochs on a single NVIDIA
-    > A100 GPU
+-   **Training Procedure**: Fine-tuned for 3 epochs on a single NVIDIA A100 GPU
 
 -   **Hyperparameters**: Learning rate: 2e-5, batch size: 16
 
@@ -101,14 +90,11 @@ pip install safetensors transformers
 
 ## **Limitations**
 
--   Supports very few functions since this was an experimental model,
-    > maybe I will add other functions later.
+-   Supports very few functions since this was an experimental model, maybe I will add other functions later.
 
--   Limited to geometry-related tasks and may not generalize to other
-    > mathematical domains.
+-   Limited to geometry-related tasks and may not generalize to other mathematical domains.
 
--   Extensive use of strict System Prompting. I aim to eliminate that
-    > also.
+-   Extensive use of strict System Prompting. I aim to eliminate that also.
 
 ## **How to Contribute**