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

Support using mmap when applying LoRA (#2095)

Browse source 
* Support using mmap when applying LoRA

* Fix Linux

* Update comment to reflect the support lora with mmap
This commit is contained in:
Howard Su 2023-07-11 22:37:01 +08:00 • committed by GitHub
parent bbef28218f
commit 2347463201
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 7 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/common.cpp
View file

@ -267,7 +267,6 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
break;
}
params.lora_adapter = argv[i];
params.use_mmap = false;
} else if (arg == "--lora-base") {
if (++i >= argc) {
invalid_param = true;
@ -499,7 +498,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stderr, " --mtest compute maximum memory usage\n");
fprintf(stderr, " --export export the computation graph to 'llama.ggml'\n");
fprintf(stderr, " --verbose-prompt print prompt before generation\n");
fprintf(stderr, " --lora FNAME apply LoRA adapter (implies --no-mmap)\n");
fprintf(stderr, " --lora FNAME apply LoRA adapter\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());