From 51dbcf2693570ae8dfaee7b058746cd32dc84da7 Mon Sep 17 00:00:00 2001 From: Andrei Betlen Date: Tue, 4 Apr 2023 22:36:59 -0400 Subject: [PATCH] Bugfix: wrong signature for quantize function --- llama_cpp/llama_cpp.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/llama_cpp/llama_cpp.py b/llama_cpp/llama_cpp.py index 5364e05..41055bd 100644 --- a/llama_cpp/llama_cpp.py +++ b/llama_cpp/llama_cpp.py @@ -125,12 +125,12 @@ _lib.llama_free.restype = None # TODO: not great API - very likely to change # Returns 0 on success def llama_model_quantize( - fname_inp: bytes, fname_out: bytes, itype: c_int, qk: c_int + fname_inp: bytes, fname_out: bytes, itype: c_int ) -> c_int: - return _lib.llama_model_quantize(fname_inp, fname_out, itype, qk) + return _lib.llama_model_quantize(fname_inp, fname_out, itype) -_lib.llama_model_quantize.argtypes = [c_char_p, c_char_p, c_int, c_int] +_lib.llama_model_quantize.argtypes = [c_char_p, c_char_p, c_int] _lib.llama_model_quantize.restype = c_int # Returns the KV cache that will contain the context for the