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 532c173

Browse filesBrowse files
authored
llama : make general.name optional (ggml-org#6709)
1 parent 666867b commit 532c173
Copy full SHA for 532c173

File tree

Expand file treeCollapse file tree

1 file changed

+3
-1
lines changed
Filter options
Expand file treeCollapse file tree

1 file changed

+3
-1
lines changed

‎llama.cpp

Copy file name to clipboardExpand all lines: llama.cpp
+3-1Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4136,9 +4136,11 @@ static void llm_load_vocab(
41364136
// CodeGemma (LLM_ARCH_GEMMA). This can potentially be removed once
41374137
// new versions of these models have been published.
41384138
std::string gen_name;
4139-
ml.get_key(LLM_KV_GENERAL_NAME, gen_name);
4139+
ml.get_key(LLM_KV_GENERAL_NAME, gen_name, false);
4140+
41404141
std::transform(gen_name.begin(), gen_name.end(), gen_name.begin(),
41414142
[](unsigned char c){ return std::tolower(c); });
4143+
41424144
if (gen_name.find("code") != std::string::npos) {
41434145
if (model.arch == LLM_ARCH_LLAMA) {
41444146
vocab.special_prefix_id = 32007;

0 commit comments

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