TheBloke/Open_Gpt4_8x7B-GGUF
Not comparable yet vs rombodawg/Open_Gpt4_8x7B_v0.1. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (227 of 995/995 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs rombodawg/Open_Gpt4_8x7B_v0.1. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (227 of 995/995 match), usually an architecture llama.cpp's name map doesn't cover yet.