nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ggml : increased GGML_MAX_PARAMS to allow finetuning of 70b models (#4424)

This commit is contained in:
Taikono-Himazin 2023-12-12 18:24:32 +09:00 committed by GitHub
parent a43b1ac59b
commit 62d88b8839
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml.h
View File

@ -215,7 +215,7 @@
#define GGML_QNT_VERSION_FACTOR 1000 // do not change this
#define GGML_MAX_DIMS 4
#define GGML_MAX_PARAMS 1024
#define GGML_MAX_PARAMS 2048
#define GGML_MAX_CONTEXTS 64
#define GGML_MAX_SRC 6
#define GGML_MAX_NAME 64