convert_hf_to_gguf.py was changed with respect to granite-4.0-small
#2
by dlippold - opened
In the last days further work was done for the support of the model granite-4.0-small by llama.cpp (https://github.com/ggml-org/llama.cpp/pull/15641), in particular for the embedding. As part of that the script convert_hf_to_gguf.py (https://github.com/ggml-org/llama.cpp/blob/master/convert_hf_to_gguf.py) was changed (https://github.com/ggml-org/llama.cpp/commit/dfc959b886d2613a4d3f06d8f3523628c654e8a3).
Is it reasonable to generate the GGUF files anew?