github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-09-06 19:10:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

llamamodel: fix semantic typo in nomic client dynamic mode (#2216)

Browse Source 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
This commit is contained in:
Jared Van Bortel
2024-04-12 17:25:15 -04:00
committed by GitHub
parent 46818e466e
commit 3f8257c563
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gpt4all-backend/llamamodel.cpp
View File

@@ -302,8 +302,8 @@ bool LLamaModel::loadModel(const std::string &modelPath, int n_ctx, int ngl)
if (llama_verbose()) {
std::cerr << "llama.cpp: using Metal" << std::endl;
d_ptr->backend_name = "metal";
}
d_ptr->backend_name = "metal";
// always fully offload on Metal
// TODO(cebtenzzre): use this parameter to allow using more than 53% of system RAM to load a model