root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-28 12:24:35 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

common : change defaults [no ci]

Browse Source
This commit is contained in:
Georgi Gerganov 2024-11-24 15:39:07 +02:00
parent 7f9cc2058c
commit 4eb126fff0
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
common/common.h
View File

@ -157,8 +157,8 @@ struct common_params_sampling {
struct common_params_speculative { struct common_params_speculative {
int32_t n_ctx = 4096; // draft context size int32_t n_ctx = 4096; // draft context size
int32_t n_max = 5; // maximum number of tokens to draft during speculative decoding int32_t n_max = 16; // maximum number of tokens to draft during speculative decoding
int32_t n_min = 0; // minimum number of draft tokens to use for speculative decoding int32_t n_min = 5; // minimum number of draft tokens to use for speculative decoding
int32_t n_gpu_layers = -1; // number of layers to store in VRAM for the draft model (-1 - use default) int32_t n_gpu_layers = -1; // number of layers to store in VRAM for the draft model (-1 - use default)
float p_split = 0.1f; // speculative decoding split probability float p_split = 0.1f; // speculative decoding split probability
float p_min = 0.9f; // minimum speculative decoding probability (greedy) float p_min = 0.9f; // minimum speculative decoding probability (greedy)