diff options
| author | pudepiedj <pudepiedj@gmail.com> | 2024-01-11 16:14:52 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-01-11 18:14:52 +0200 |
| commit | 43f76bf1c362c067fce46bb8dcda0b64af8a9533 (patch) | |
| tree | c446cabb97601363b645f2fb661bc48d790478fa /common/common.h | |
| parent | 2f043328e3116724d15b915b5c6078e2df860a69 (diff) | |
main : print total token count and tokens consumed so far (#4874)
* Token count changes
* Add show token count
* Updating before PR
* Two requested changes
* Move param def posn
Diffstat (limited to 'common/common.h')
| -rw-r--r-- | common/common.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/common/common.h b/common/common.h index e2bbfc25..a295e88b 100644 --- a/common/common.h +++ b/common/common.h @@ -64,6 +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 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 @@ -242,4 +243,3 @@ void dump_kv_cache_view(const llama_kv_cache_view & view, int row_size = 80); // Dump the KV cache view showing individual sequences in each cell (long output). void dump_kv_cache_view_seqs(const llama_kv_cache_view & view, int row_size = 40); - |