TabunKaze/Basil
Not comparable yet vs unsloth/Meta-Llama-3.1-8B-Instruct. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 291/255 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs unsloth/Meta-Llama-3.1-8B-Instruct. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 291/255 match), usually an architecture llama.cpp's name map doesn't cover yet.