Perform a naming refactor in order to clearly notate the model family (i.e. Llama, Mistral, Qwen, etc) as family and the different model quantizations (i.e. FP16, Q8_0 etc) as quantization because currently, those two different things are both referred as model type throughout the code and classes and lead to confusions.
Perform a naming refactor in order to clearly notate the model family (i.e. Llama, Mistral, Qwen, etc) as
familyand the different model quantizations (i.e.FP16,Q8_0etc) asquantizationbecause currently, those two different things are both referred asmodel typethroughout the code and classes and lead to confusions.