diff options
| author | Georgi Gerganov <ggerganov@gmail.com> | 2024-01-11 22:43:05 +0200 |
|---|---|---|
| committer | Georgi Gerganov <ggerganov@gmail.com> | 2024-01-11 22:43:05 +0200 |
| commit | 3ca63b4538dfc78aaec88cd2c3e3f8417c1924e3 (patch) | |
| tree | 741167ae638864d1943d72adc9fd72b249f99437 | |
| parent | b0377875488b33f7114138687d828da1de61775d (diff) | |
main : disable token count by default (#4874)
| -rw-r--r-- | common/common.cpp | 6 | ||||
| -rw-r--r-- | common/common.h | 2 | ||||
| -rw-r--r-- | examples/main/main.cpp | 4 |
3 files changed, 6 insertions, 6 deletions
diff --git a/common/common.cpp b/common/common.cpp index bfcd6d4d..287e8bd5 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -630,7 +630,7 @@ 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") { + } else if (arg == "-stc" || arg == "--show-token-count") { if (++i >= argc) { invalid_param = true; 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(" 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(" -stc N --show-token-count N\n"); + printf(" show consumed tokens every N tokens (default: %d)\n", params.token_interval); printf("\n"); #ifndef LOG_DISABLE_LOGS log_print_usage(); diff --git a/common/common.h b/common/common.h index a295e88b..82d23cf5 100644 --- a/common/common.h +++ b/common/common.h @@ -64,7 +64,7 @@ struct gpt_params { 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_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_scale = 0.0f; // RoPE frequency scaling factor float yarn_ext_factor = -1.0f; // YaRN extrapolation mix factor diff --git a/examples/main/main.cpp b/examples/main/main.cpp index 1f35febb..6953d107 100644 --- a/examples/main/main.cpp +++ b/examples/main/main.cpp @@ -651,8 +651,8 @@ int main(int argc, char ** argv) { 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 (params.token_interval > 0 && n_past % params.token_interval == 0) { + LOG_TEE("\n\033[31mTokens consumed so far = %d / %d \033[0m\n", n_past, n_ctx); } } |