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

n_keep help update

Browse source
This commit is contained in:
anzz1 2023-03-28 16:54:29 +03:00 • committed by GitHub
parent ebf09a1919
commit 51266e4ae7
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/common.cpp
View file

@ -213,7 +213,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stderr, " --in-prefix STRING string to prefix user inputs with (default: empty)\n");
fprintf(stderr, " -f FNAME, --file FNAME\n");
fprintf(stderr, " prompt file to start generation.\n");
fprintf(stderr, " -n N, --n_predict N number of tokens to predict (default: %d, -1 - infinity)\n", params.n_predict);
fprintf(stderr, " -n N, --n_predict N number of tokens to predict (default: %d, -1 = infinity)\n", params.n_predict);
fprintf(stderr, " --top_k N top-k sampling (default: %d)\n", params.top_k);
fprintf(stderr, " --top_p N top-p sampling (default: %.1f)\n", params.top_p);
fprintf(stderr, " --repeat_last_n N last n tokens to consider for penalize (default: %d)\n", params.repeat_last_n);
@ -225,7 +225,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stderr, " --n_parts N number of model parts (default: -1 = determine from dimensions)\n");
fprintf(stderr, " -b N, --batch_size N batch size for prompt processing (default: %d)\n", params.n_batch);
fprintf(stderr, " --perplexity compute perplexity over the prompt\n");
fprintf(stderr, " --keep number of tokens to keep from the initial prompt\n");
fprintf(stderr, " --keep number of tokens to keep from the initial prompt (default: %d, -1 = all)\n", params.n_keep);
if (ggml_mlock_supported()) {
fprintf(stderr, " --mlock force system to keep model in RAM rather than swapping or compressing\n");
}