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

Add --n-predict -2 for stopping generation on full context (#2565)

Browse source
This commit is contained in:
Christian Demsar 2023-08-10 10:28:27 -04:00 • committed by GitHub
parent 1638757767
commit e59fcb2bc1
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 12 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/common.cpp
View file

@ -543,7 +543,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stdout, " --in-suffix STRING string to suffix after user inputs with (default: empty)\n");
fprintf(stdout, " -f FNAME, --file FNAME\n");
fprintf(stdout, " prompt file to start generation.\n");
fprintf(stdout, " -n N, --n-predict N number of tokens to predict (default: %d, -1 = infinity)\n", params.n_predict);
fprintf(stdout, " -n N, --n-predict N number of tokens to predict (default: %d, -1 = infinity, -2 = until context filled)\n", params.n_predict);
fprintf(stdout, " -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx);
fprintf(stdout, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
fprintf(stdout, " -gqa N, --gqa N grouped-query attention factor (TEMP!!! use 8 for LLaMAv2 70B) (default: %d)\n", params.n_gqa);