FYI: GGUF naming convention and llama.cpp -hf tags
#1
by Serveurperso - opened
Small FYI: llama.cpp -hf tags (like :Q4_K_M) only match when the quant is separated by a dash, as in the GGUF naming convention (https://github.com/ggml-org/ggml/blob/master/docs/gguf.md#gguf-naming-convention). Using model-Q4_K_M.gguf instead of model_Q4_K_M.gguf in future uploads would make them work with it. Thanks!
thanks