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

cmdline option for custom amount of model parts (--n_parts N) (#348)

Browse source 
* cmdline option for custom amount of model parts (--n_parts N)

* Update main.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
anzz1 2023-03-21 17:42:43 +02:00 • committed by GitHub
parent e0ffc861fa
commit 975d2cebf9
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 12 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

3
utils.cpp
View file

@ -74,6 +74,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
params.antiprompt.push_back(argv[++i]);
} else if (arg == "--ignore-eos") {
params.ignore_eos = true;
} else if (arg == "--n_parts") {
params.n_parts = std::stoi(argv[++i]);
} else if (arg == "-h" || arg == "--help") {
gpt_print_usage(argc, argv, params);
exit(0);
@ -116,6 +118,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stderr, " --ignore-eos ignore end of stream token and continue generating\n");
fprintf(stderr, " --memory_f16 use f16 instead of f32 for memory key+value\n");
fprintf(stderr, " --temp N temperature (default: %.1f)\n", params.temp);
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, " -m FNAME, --model FNAME\n");
fprintf(stderr, " model path (default: %s)\n", params.model.c_str());