Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 01:31:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into concedo_experimental

Browse Source 
# Conflicts:
#	README.md
This commit is contained in:
Concedo
2023-05-09 16:50:43 +08:00
parent e4c6a1e3ed 41654efea8
commit 54194911ac
9 changed files with 488 additions and 129 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gpttype_adapter.cpp
+1 -1
View File
@@ -264,7 +264,7 @@ ModelLoadResult gpttype_load_model(const load_model_inputs inputs, FileFormat in
}
//determine mem per token
const std::vector<int> tmp = {0, 1, 2, 3};
const std::vector<int> tmp = {1, 2, 3, 4};
llama_eval(llama_ctx_v1, tmp.data(), tmp.size(), 0, params.n_threads);
return ModelLoadResult::SUCCESS;