alihan/llama-cpp-python
1
0
Fork 0
mirror of https://github.com/abetlen/llama-cpp-python.git synced 2023-09-07 17:34:22 +03:00
Code Issues Packages Projects Releases Wiki Activity

Bugfix: wrong signature for quantize function

Browse Source
This commit is contained in:
Andrei Betlen
2023-04-04 22:36:59 -04:00
parent 8279fb7d92
commit 51dbcf2693
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
llama_cpp/llama_cpp.py
View File

@@ -125,12 +125,12 @@ _lib.llama_free.restype = None
# TODO: not great API - very likely to change # TODO: not great API - very likely to change
# Returns 0 on success # Returns 0 on success
def llama_model_quantize( 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: ) -> 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 _lib.llama_model_quantize.restype = c_int
# Returns the KV cache that will contain the context for the # Returns the KV cache that will contain the context for the