Upload Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw-Q8_0-imat.gguf

Upload Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw-Q6_K-imat.gguf

Upload Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw-Q5_K_S-imat.gguf

Upload Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw-Q5_K_M-imat.gguf

Upload Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw-Q4_K_S-imat.gguf

Upload Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw-Q4_K_M-imat.gguf

Upload Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw-IQ4_XS-imat.gguf

Upload Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw-IQ4_NL-imat.gguf

Upload Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw-IQ3_M-imat.gguf

Added initial model-card elements to README

Added GGUF generation script and configuration, please brief note

Added script used to generate GGUF files

README, imatrix used, and IQ3_XXS GGUF model

initial commit