millaguie/llama.cpp
1
0 Fork 0
Code Issues Pull Requests Actions 32 Packages Projects Releases Wiki Activity

llama : valign + remove unused ftype (#8502)

Browse Source
This commit is contained in:
Georgi Gerganov authored and GitHub committed 2024-07-16 10:00:30 +03:00
1 parent 7acfd4e8d5
commit 0efec57787
3 files changed
+72 -76
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

include/llama.h
+1 -1
View File
@@ -133,7 +133,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_F16 = 1, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_0 = 2, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_1 = 3, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16 = 4, // tok_embeddings.weight and output.weight are F16
// LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16 = 4, // tok_embeddings.weight and output.weight are F16
// LLAMA_FTYPE_MOSTLY_Q4_2 = 5, // support has been removed
// LLAMA_FTYPE_MOSTLY_Q4_3 = 6, // support has been removed
LLAMA_FTYPE_MOSTLY_Q8_0 = 7, // except 1d tensors