Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

Commit 005c78d

Browse filesBrowse files
abetlenabetlen
committed
Update llama.cpp
1 parent c854c25 commit 005c78d
Copy full SHA for 005c78d

File tree

Expand file treeCollapse file tree

2 files changed

+2
-1
lines changed
Filter options
Expand file treeCollapse file tree

2 files changed

+2
-1
lines changed

‎llama_cpp/llama_cpp.py

Copy file name to clipboardExpand all lines: llama_cpp/llama_cpp.py
+1Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -114,6 +114,7 @@ class llama_context_params(Structure):
114114
LLAMA_FTYPE_MOSTLY_F16 = ctypes.c_int(1) # except 1d tensors
115115
LLAMA_FTYPE_MOSTLY_Q4_0 = ctypes.c_int(2) # except 1d tensors
116116
LLAMA_FTYPE_MOSTLY_Q4_1 = ctypes.c_int(3) # except 1d tensors
117+
LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16 = ctypes.c_int(4) # tok_embeddings.weight and output.weight are F16
117118

118119
# Functions
119120

‎vendor/llama.cpp

Copy file name to clipboard

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.