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

Merge branch 'master' into add_stop_token

Browse source
This commit is contained in:
Jason McCartney 2023-05-11 10:26:00 -07:00
commit 099a07fb87
26 changed files with 3100 additions and 928 deletions
Download patch file Download diff file Expand all files Collapse all files

15
examples/common.cpp
View file

@ -139,6 +139,19 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
break;
}
params.model = argv[i];
} else if (arg == "--lora") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.lora_adapter = argv[i];
params.use_mmap = false;
} else if (arg == "--lora-base") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.lora_base = argv[i];
} else if (arg == "-i" || arg == "--interactive") {
params.interactive = true;
} else if (arg == "--embedding") {
@ -243,6 +256,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
}
fprintf(stderr, " --mtest compute maximum memory usage\n");
fprintf(stderr, " --verbose-prompt print prompt before generation\n");
fprintf(stderr, " --lora FNAME apply LoRA adapter (implies --no-mmap)\n");
fprintf(stderr, " --lora-base FNAME optional model to use as a base for the layers modified by the LoRA adapter\n");
fprintf(stderr, " -m FNAME, --model FNAME\n");
fprintf(stderr, " model path (default: %s)\n", params.model.c_str());
fprintf(stderr, "\n");