vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : remove Q4_2 mode

Browse source
This commit is contained in:
Georgi Gerganov 2023-05-07 18:26:59 +03:00
parent b47bd2877f
commit 7cdc08a5d1
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
7 changed files with 8 additions and 366 deletions
Download patch file Download diff file Expand all files Collapse all files

11
examples/quantize/quantize.cpp
View file

@ -7,12 +7,11 @@
#include <string>
static const std::map<std::string, llama_ftype> LLAMA_FTYPE_MAP = {
{"q4_0", LLAMA_FTYPE_MOSTLY_Q4_0},
{"q4_1", LLAMA_FTYPE_MOSTLY_Q4_1},
{"q4_2", LLAMA_FTYPE_MOSTLY_Q4_2},
{"q5_0", LLAMA_FTYPE_MOSTLY_Q5_0},
{"q5_1", LLAMA_FTYPE_MOSTLY_Q5_1},
{"q8_0", LLAMA_FTYPE_MOSTLY_Q8_0},
{"q4_0", LLAMA_FTYPE_MOSTLY_Q4_0},
{"q4_1", LLAMA_FTYPE_MOSTLY_Q4_1},
{"q5_0", LLAMA_FTYPE_MOSTLY_Q5_0},
{"q5_1", LLAMA_FTYPE_MOSTLY_Q5_1},
{"q8_0", LLAMA_FTYPE_MOSTLY_Q8_0},
};
bool try_parse_ftype(const std::string & ftype_str, llama_ftype & ftype, std::string & ftype_str_out) {