mirrors/cosmopolitan
1
0
Fork 0
mirror of https://github.com/jart/cosmopolitan.git synced 2025-02-07 06:53:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Make llama.com n_predict be -1 by default

Browse source
This commit is contained in:
Justine Tunney 2023-05-12 08:20:34 -07:00
parent ca19ecf49c
commit bbfe4fbd11
No known key found for this signature in database
GPG key ID: BE714B4575D6E328
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
third_party/ggml/common.h vendored
View file

@ -22,7 +22,7 @@ struct gpt_params {
int32_t seed = -1; // RNG seed
int32_t verbose = 0; // Logging verbosity
int32_t n_threads = std::min(1, (int)(_getcpucount() * 0.75));
int32_t n_predict = 128; // new tokens to predict
int32_t n_predict = -1; // new tokens to predict
int32_t n_parts = -1; // amount of model parts (-1 = determine from model dimensions)
int32_t n_ctx = 512; // context size
int32_t n_batch = 64; // batch size for prompt processing (must be >=32 to use BLAS)