tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-29 05:33:37 -04:00
Code Issues Packages Projects Releases Wiki Activity

Default to 4 threads (#243)

Browse Source
This commit is contained in:
Georgi Gerganov
2023-03-17 21:46:46 +02:00
parent e81b9c81c1
commit 4f54609110
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
utils.h
View File

@@ -14,11 +14,11 @@
struct gpt_params { struct gpt_params {
int32_t seed = -1; // RNG seed int32_t seed = -1; // RNG seed
int32_t n_threads; int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency());
int32_t n_predict = 128; // new tokens to predict int32_t n_predict = 128; // new tokens to predict
int32_t repeat_last_n = 64; // last n tokens to penalize int32_t repeat_last_n = 64; // last n tokens to penalize
int32_t n_ctx = 512; //context size int32_t n_ctx = 512; //context size
// sampling parameters // sampling parameters
int32_t top_k = 40; int32_t top_k = 40;
float top_p = 0.95f; float top_p = 0.95f;