tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

main : print total token count and tokens consumed so far (#4874)

Browse Source 
* Token count changes

* Add show token count

* Updating before PR

* Two requested changes

* Move param def posn
This commit is contained in:
pudepiedj
2024-01-11 16:14:52 +00:00
committed by GitHub
parent 2f043328e3
commit 43f76bf1c3
4 changed files with 15 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/main/main.cpp
View File

@ -500,7 +500,7 @@ int main(int argc, char ** argv) {
while ((n_remain != 0 && !is_antiprompt) || params.interactive) {
// predict
if (!embd.empty()) {
// Note: n_ctx - 4 here is to match the logic for commandline prompt handling via
// Note: (n_ctx - 4) here is to match the logic for commandline prompt handling via
// --prompt or --file which uses the same value.
int max_embd_size = n_ctx - 4;
@ -650,6 +650,10 @@ int main(int argc, char ** argv) {
n_past += n_eval;
LOG("n_past = %d\n", n_past);
// Display total tokens alongside total time
if (n_past % params.token_interval == 0) {
printf("\n\033[31mTokens consumed so far = %d / %d \033[0m\n", n_past, n_ctx);
}
}
if (!embd.empty() && !path_session.empty()) {