Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 05:48:47 +01:00
Code Issues Packages Projects Releases Wiki Activity

main : disable token count by default (#4874)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-01-11 22:43:05 +02:00
parent b037787548
commit 3ca63b4538
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
3 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
common/common.cpp
View File

@ -630,7 +630,7 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
break; break;
} }
params.ppl_stride = std::stoi(argv[i]); params.ppl_stride = std::stoi(argv[i]);
} else if (arg == "-stc" || arg == "--show_token_count") { } else if (arg == "-stc" || arg == "--show-token-count") {
if (++i >= argc) { if (++i >= argc) {
invalid_param = true; invalid_param = true;
break; break;
@ -950,8 +950,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" --override-kv KEY=TYPE:VALUE\n"); printf(" --override-kv KEY=TYPE:VALUE\n");
printf(" advanced option to override model metadata by key. may be specified multiple times.\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(" types: int, float, bool. example: --override-kv tokenizer.ggml.add_bos_token=bool:false\n");
printf(" -stc N --show_token_count N\n"); printf(" -stc N --show-token-count N\n");
printf(" show consumed tokens every N tokens\n"); printf(" show consumed tokens every N tokens (default: %d)\n", params.token_interval);
printf("\n"); printf("\n");
#ifndef LOG_DISABLE_LOGS #ifndef LOG_DISABLE_LOGS
log_print_usage(); log_print_usage();

2
common/common.h
View File

@ -64,7 +64,7 @@ struct gpt_params {
int32_t n_beams = 0; // if non-zero then use beam search of given width. int32_t n_beams = 0; // if non-zero then use beam search of given width.
int32_t grp_attn_n = 1; // group-attention factor int32_t grp_attn_n = 1; // group-attention factor
int32_t grp_attn_w = 512; // group-attention width int32_t grp_attn_w = 512; // group-attention width
int32_t token_interval = 512; // show token count every 512 tokens int32_t token_interval = -1; // show token count every 512 tokens (-1 = disabled)
float rope_freq_base = 0.0f; // RoPE base frequency float rope_freq_base = 0.0f; // RoPE base frequency
float rope_freq_scale = 0.0f; // RoPE frequency scaling factor float rope_freq_scale = 0.0f; // RoPE frequency scaling factor
float yarn_ext_factor = -1.0f; // YaRN extrapolation mix factor float yarn_ext_factor = -1.0f; // YaRN extrapolation mix factor

4
examples/main/main.cpp
View File

@ -651,8 +651,8 @@ int main(int argc, char ** argv) {
LOG("n_past = %d\n", n_past); LOG("n_past = %d\n", n_past);
// Display total tokens alongside total time // Display total tokens alongside total time
if (n_past % params.token_interval == 0) { if (params.token_interval > 0 && n_past % params.token_interval == 0) {
printf("\n\033[31mTokens consumed so far = %d / %d \033[0m\n", n_past, n_ctx); LOG_TEE("\n\033[31mTokens consumed so far = %d / %d \033[0m\n", n_past, n_ctx);
} }
} }