tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-02 05:15:47 +00:00
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
3 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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 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