vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update batch size for efficiency

Browse source
This commit is contained in:
Gary Linscott 2023-04-13 08:20:54 -07:00
parent fbcecd59a9
commit 23fd782d35
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/perplexity/perplexity.cpp
View file

@ -86,11 +86,13 @@ int main(int argc, char ** argv) {
gpt_params params;
params.model = "models/llama-7B/ggml-model.bin";
params.n_batch = 512;
if (gpt_params_parse(argc, argv, params) == false) {
return 1;
}
params.perplexity = true;
params.n_batch = std::min(params.n_batch, params.n_ctx);
if (params.n_ctx > 2048) {
fprintf(stderr, "%s: warning: model does not support context sizes greater than 2048 tokens (%d specified);"