From 43f76bf1c362c067fce46bb8dcda0b64af8a9533 Mon Sep 17 00:00:00 2001 From: pudepiedj Date: Thu, 11 Jan 2024 16:14:52 +0000 Subject: 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 --- common/common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'common/common.h') 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); - -- cgit v1.2.3