Skip to main content

baseRT_encode_pieces

Function baseRT_encode_pieces 

Source
pub unsafe extern "C" fn baseRT_encode_pieces(
    model: baseRT_model_t,
    texts: *const *const c_char,
    plain: *const c_int,
    n_pieces: c_int,
    out_tokens: *mut u32,
    max_tokens: c_int,
) -> c_int
Expand description

n_pieces texts encoded as one: piece i parses marker strings when plain[i] is zero and keeps them as text otherwise, with the pre-tokenizer seeing the concatenation. See the header.