tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 20:05:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove Q4_3 which is no better than Q5 (#1218)

Browse Source
This commit is contained in:
Stephan Walter
2023-04-28 23:10:43 +00:00
committed by GitHub
parent 7f15c5c477
commit 36d19a603b
11 changed files with 21 additions and 359 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@ -9,7 +9,6 @@ static const std::map<std::string, enum 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},
{"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},