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

added ctx_size parameter (#148)

Browse Source 
* added ctx_size parameter

* added it in more places

* Apply suggestions from code review

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Justin Suess
2023-03-15 15:42:40 -04:00
committed by GitHub
parent 16b2c61a22
commit 2d64715ad4
3 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
utils.h
View File

@ -17,7 +17,8 @@ struct gpt_params {
int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency());
int32_t n_predict = 128; // new tokens to predict
int32_t repeat_last_n = 64; // last n tokens to penalize
int32_t n_ctx = 512; //context size
// sampling parameters
int32_t top_k = 40;
float top_p = 0.95f;