tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +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

8
common/common.cpp
View File

@ -630,6 +630,12 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
break;
}
params.ppl_stride = std::stoi(argv[i]);
} else if (arg == "-stc" || arg == "--show_token_count") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.token_interval = std::stoi(argv[i]);
} else if (arg == "--ppl-output-type") {
if (++i >= argc) {
invalid_param = true;
@ -944,6 +950,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" --override-kv KEY=TYPE:VALUE\n");
printf(" advanced option to override model metadata by key. may be specified multiple times.\n");
printf(" types: int, float, bool. example: --override-kv tokenizer.ggml.add_bos_token=bool:false\n");
printf(" -stc N --show_token_count N\n");
printf(" show consumed tokens every N tokens\n");
printf("\n");
#ifndef LOG_DISABLE_LOGS
log_print_usage();