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

quantize : add Q5_0 and Q5_1 to map

Browse source
This commit is contained in:
Georgi Gerganov 2023-04-26 20:45:03 +03:00
parent 8e936ad0cd
commit 982bfce678
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/quantize/quantize.cpp
View file

@ -10,6 +10,8 @@ static const std::map<std::string, enum llama_ftype> LLAMA_FTYPE_MAP = {
{"q4_1", LLAMA_FTYPE_MOSTLY_Q4_1},
{"q4_2", LLAMA_FTYPE_MOSTLY_Q4_2},
{"q4_3", LLAMA_FTYPE_MOSTLY_Q4_3},
{"q5_0", LLAMA_FTYPE_MOSTLY_Q5_0},
{"q5_1", LLAMA_FTYPE_MOSTLY_Q5_1},
{"q8_0", LLAMA_FTYPE_MOSTLY_Q8_0},
};