Struct GgufConfigInputs 

pub struct GgufConfigInputs<'a> {
    pub meta: &'a dyn GgufMeta,
    pub token_embd_vocab: Option<usize>,
    pub has_output_weight: bool,
}

Inputs to config_from_gguf: the metadata accessor plus two facts the builder needs from the tensor section (not the metadata KV block).

Fields

meta: &'a dyn GgufMeta

token_embd_vocab: Option<usize>

Rows of token_embd.weight — the authoritative vocab size when the {arch}.vocab_size key is absent. None if the loader could not read the tensor shape before building the config.

has_output_weight: bool

Whether the file contains an output.weight tensor. Its presence means an untied LM head; its absence means the LM head ties to the input embeddings. GGUF has no explicit tie_word_embeddings key, so this is the only reliable signal.