github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-09-10 04:49:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

bump mem allocation a bit

Browse Source
This commit is contained in:
Aaron Miller
2023-07-13 18:24:01 -04:00
committed by AT
parent 936dcd2bfc
commit 1c4a244291
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gpt4all-backend/bert.cpp
View File

@@ -871,7 +871,7 @@ struct bert_ctx * bert_load_from_file(const char *fname)
// TODO: Max tokens should be a param? // TODO: Max tokens should be a param?
int32_t N = new_bert->model.hparams.n_max_tokens; int32_t N = new_bert->model.hparams.n_max_tokens;
new_bert->mem_per_input = 1.9 * (new_bert->mem_per_token * N); // add 10% to account for ggml object overhead new_bert->mem_per_input = 2.2 * (new_bert->mem_per_token * N); // add 10% to account for ggml object overhead
} }
#if defined(DEBUG_BERT) #if defined(DEBUG_BERT)