Model Export

[simony05]

• Build a function to export the model weights to be usable in the system components
• Build a function to quantize model weights (From Google: Quantization in machine learning is a model optimization technique that reduces the precision of a model's weights and activations (e.g., from 32-bit floats to 8-bit integers) to decrease its size, lower memory usage, and speed up inference, making it ideal for deployment on resource-constrained devices, though it can slightly reduce accuracy)