CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

common : warm-up with 2 tokens - seems to work better

Browse Source
This commit is contained in:
Georgi Gerganov
2023-09-03 21:07:01 +03:00
parent 013457885a
commit ebe41d49a6
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/common.cpp
View File

@@ -770,7 +770,7 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
{ {
LOG("warming up the model with an empty run\n"); LOG("warming up the model with an empty run\n");
const std::vector<llama_token> tmp = { llama_token_bos(lctx), }; const std::vector<llama_token> tmp = { llama_token_bos(lctx), llama_token_eos(lctx), };
llama_eval(lctx, tmp.data(), tmp.size(), 0, params.n_threads); llama_eval(lctx, tmp.data(), tmp.size(), 0, params.n_threads);
llama_reset_timings(lctx); llama_reset_timings(lctx);
} }