Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-02 02:51:17 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '584d674be622fbf1578694ada6e62eebedbfd377' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/nix-flake-update.yml
#	Makefile
#	Package.swift
#	ggml-cuda.cu
#	tests/test-quantize-fns.cpp
This commit is contained in:
Concedo
2024-01-14 16:29:44 +08:00
parent bd77a48037 584d674be6
commit dc7bc0cb50
31 changed files with 2138 additions and 386 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+13 -2
View File
@@ -631,6 +631,12 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
break;
}
params.ppl_stride = std::stoi(argv[i]);
} else if (arg == "-ptc" || arg == "--print-token-count") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.n_print = std::stoi(argv[i]);
} else if (arg == "--ppl-output-type") {
if (++i >= argc) {
invalid_param = true;
@@ -813,7 +819,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf("\n");
printf("options:\n");
printf(" -h, --help show this help message and exit\n");
printf(" --version show version and build info\n");
printf(" --version show version and build info\n");
printf(" -i, --interactive run in interactive mode\n");
printf(" --interactive-first run in interactive mode and wait for input right away\n");
printf(" -ins, --instruct run in instruction mode (use with Alpaca models)\n");
@@ -910,7 +916,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" number of layers to store in VRAM\n");
printf(" -ngld N, --n-gpu-layers-draft N\n");
printf(" number of layers to store in VRAM for the draft model\n");
printf(" -ts SPLIT --tensor-split SPLIT\n");
printf(" -ts SPLIT, --tensor-split SPLIT\n");
printf(" how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n");
printf(" -mg i, --main-gpu i the GPU to use for scratch and small tensors\n");
#ifdef GGML_USE_CUBLAS
@@ -945,6 +951,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" --override-kv KEY=TYPE:VALUE\n");
printf(" advanced option to override model metadata by key. may be specified multiple times.\n");
printf(" types: int, float, bool. example: --override-kv tokenizer.ggml.add_bos_token=bool:false\n");
printf(" -ptc N, --print-token-count N\n");
printf(" print token count every N tokens (default: %d)\n", params.n_print);
printf("\n");
#ifndef LOG_DISABLE_LOGS
log_print_usage();
@@ -1048,6 +1056,9 @@ struct llama_model_params llama_model_params_from_gpt_params(const gpt_params &
}
static ggml_type kv_cache_type_from_str(const std::string & s) {
if (s == "f32") {
return GGML_TYPE_F32;
}
if (s == "f16") {
return GGML_TYPE_F16;
}