vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	.gitignore
#	CMakeLists.txt
#	Makefile
#	README.md
#	ci/run.sh
#	flake.lock
#	flake.nix
#	ggml-cuda.cu
#	ggml-cuda.h
#	scripts/get-wikitext-2.sh
#	tests/CMakeLists.txt
This commit is contained in:
Concedo 2024-01-21 14:32:15 +08:00
commit 1cb8a5e955
79 changed files with 6273 additions and 2982 deletions
Download patch file Download diff file Expand all files Collapse all files

32
common/common.cpp
View file

@ -168,6 +168,24 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
if (params.n_threads_batch <= 0) {
params.n_threads_batch = std::thread::hardware_concurrency();
}
} else if (arg == "-td" || arg == "--threads-draft") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.n_threads_draft = std::stoi(argv[i]);
if (params.n_threads_draft <= 0) {
params.n_threads_draft = std::thread::hardware_concurrency();
}
} else if (arg == "-tbd" || arg == "--threads-batch-draft") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.n_threads_batch_draft = std::stoi(argv[i]);
if (params.n_threads_batch_draft <= 0) {
params.n_threads_batch_draft = std::thread::hardware_concurrency();
}
} else if (arg == "-p" || arg == "--prompt") {
if (++i >= argc) {
invalid_param = true;
@ -664,6 +682,14 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
break;
}
params.hellaswag_tasks = std::stoi(argv[i]);
} else if (arg == "--winogrande") {
params.winogrande = true;
} else if (arg == "--winogrande-tasks") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.winogrande_tasks = std::stoi(argv[i]);
} else if (arg == "--ignore-eos") {
params.ignore_eos = true;
} else if (arg == "--no-penalize-nl") {
@ -846,6 +872,10 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" -t N, --threads N number of threads to use during generation (default: %d)\n", params.n_threads);
printf(" -tb N, --threads-batch N\n");
printf(" number of threads to use during batch and prompt processing (default: same as --threads)\n");
printf(" -td N, --threads-draft N");
printf(" number of threads to use during generation (default: same as --threads)");
printf(" -tbd N, --threads-batch-draft N\n");
printf(" number of threads to use during batch and prompt processing (default: same as --threads-draft)\n");
printf(" -p PROMPT, --prompt PROMPT\n");
printf(" prompt to start generation with (default: empty)\n");
printf(" -e, --escape process prompt escapes sequences (\\n, \\r, \\t, \\', \\\", \\\\)\n");
@ -905,6 +935,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" --logits-all return logits for all tokens in the batch (default: disabled)\n");
printf(" --hellaswag compute HellaSwag score over random tasks from datafile supplied with -f\n");
printf(" --hellaswag-tasks N number of tasks to use when computing the HellaSwag score (default: %zu)\n", params.hellaswag_tasks);
printf(" --winogrande compute Winogrande score over random tasks from datafile supplied with -f\n");
printf(" --winogrande-tasks N number of tasks to use when computing the Winogrande score (default: %zu)\n", params.winogrande_tasks);
printf(" --keep N number of tokens to keep from the initial prompt (default: %d, -1 = all)\n", params.n_keep);
printf(" --draft N number of tokens to draft for speculative decoding (default: %d)\n", params.n_draft);
printf(" --chunks N max number of chunks to process (default: %d, -1 = all)\n", params.n_chunks);