Adding Llama.cpp support with quantized models

[ArthurCamara]

Adding support to Llama.cpp with quantized models.

8-bit model: https://huggingface.co/castorini/rank_vicuna_7b_v1_q8_0/ 4-bit model: https://huggingface.co/castorini/rank_vicuna_7b_v1_q4_0/