tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 12:25:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add LoRA support (#820)

Browse Source
This commit is contained in:
slaren
2023-04-17 17:28:55 +02:00
committed by GitHub
parent efd05648c8
commit 315a95a4d3
10 changed files with 753 additions and 41 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") {
@ -242,6 +255,8 @@ 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");