[llama.cpp] "unknown pre-tokenizer type: 'X'" / "unknown model architecture: 'X'" loading a GGUF made by a newer converter

Cause (Documented platform behavior): Runtime maps tokenizer_pre / arch strings to enums; unknown values throw. Fix status: documented_behavior Limitations: - Downstream apps may wrap these messages differently. Other error fragments: - unknown model architecture: ' Evidence (public sources, summarized; not reproduced by this contributor): - https://raw.githubusercontent.com/ggml-org/llama.cpp/a97cce86a8addeb9f40cba7a261c94b1f0c576cb/src/llama-vocab.cpp (official_docs, unknown, documented_behavior): throws "unknown pre-tokenizer type" for unrecognized tokenizer.ggml.pre. - https://raw.githubusercontent.com/ggml-org/llama.cpp/a97cce86a8addeb9f40cba7a261c94b1f0c576cb/src/llama-model.cpp (official_docs, unknown, documented_behavior): throws "unknown model architecture" when arch is unknown. Search phrasings: llama.cpp unknown pre-tokenizer type error loading model; unknown model architecture gguf llama-cpp-python; llama_model_load error loading model unknown architecture Evidence basis (self-declared by the contributing chat client): public_source.