vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-21 18:52:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	Makefile
#	ggml.c
#	llama.cpp
This commit is contained in:
Concedo 2023-05-14 11:34:41 +08:00
commit e01e373e63
16 changed files with 6698 additions and 350 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/CMakeLists.txt
View file

@ -36,4 +36,5 @@ else()
add_subdirectory(embedding)
add_subdirectory(save-load-state)
add_subdirectory(benchmark)
add_subdirectory(baby-llama)
endif()

4
examples/baby-llama/CMakeLists.txt Normal file
View file

@ -0,0 +1,4 @@
set(TARGET baby-llama)
add_executable(${TARGET} baby-llama.cpp)
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
target_compile_features(${TARGET} PRIVATE cxx_std_11)

1687
examples/baby-llama/baby-llama.cpp Normal file
View file

File diff suppressed because it is too large Load diff

25
examples/common.cpp
View file

@ -277,6 +277,12 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
params.use_color = true;
} else if (arg == "--mlock") {
params.use_mlock = true;
} else if (arg == "--gpu-layers" || arg == "-ngl" || arg == "--n-gpu-layers") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.n_gpu_layers = std::stoi(argv[i]);
} else if (arg == "--no-mmap") {
params.use_mmap = false;
} else if (arg == "--mtest") {
@ -421,6 +427,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
if (llama_mmap_supported()) {
fprintf(stderr, " --no-mmap do not memory-map model (slower load but may reduce pageouts if not using mlock)\n");
}
fprintf(stderr, " -ngl N, --n-gpu-layers N\n");
fprintf(stderr, " number of layers to store in VRAM\n");
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");
@ -463,14 +471,15 @@ std::vector<llama_token> llama_tokenize(struct llama_context * ctx, const std::s
struct llama_context * llama_init_from_gpt_params(const gpt_params & params) {
auto lparams = llama_context_default_params();
lparams.n_ctx = params.n_ctx;
lparams.n_parts = params.n_parts;
lparams.seed = params.seed;
lparams.f16_kv = params.memory_f16;
lparams.use_mmap = params.use_mmap;
lparams.use_mlock = params.use_mlock;
lparams.logits_all = params.perplexity;
lparams.embedding = params.embedding;
lparams.n_ctx = params.n_ctx;
lparams.n_parts = params.n_parts;
lparams.n_gpu_layers = params.n_gpu_layers;
lparams.seed = params.seed;
lparams.f16_kv = params.memory_f16;
lparams.use_mmap = params.use_mmap;
lparams.use_mlock = params.use_mlock;
lparams.logits_all = params.perplexity;
lparams.embedding = params.embedding;
llama_context * lctx = llama_init_from_file(params.model.c_str(), lparams);

11
examples/common.h
View file

@ -21,13 +21,14 @@
int32_t get_num_physical_cores();
struct gpt_params {
int32_t seed = -1; // RNG seed
int32_t seed = -1; // RNG seed
int32_t n_threads = get_num_physical_cores();
int32_t n_predict = -1; // new tokens to predict
int32_t n_parts = -1; // amount of model parts (-1 = determine from model dimensions)
int32_t n_ctx = 512; // context size
int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_keep = 0; // number of tokens to keep from initial prompt
int32_t n_parts = -1; // amount of model parts (-1 = determine from model dimensions)
int32_t n_ctx = 512; // context size
int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_keep = 0; // number of tokens to keep from initial prompt
int32_t n_gpu_layers = 0; // number of layers to store in VRAM
// sampling parameters
std::unordered_map<llama_token, float> logit_bias; // logit bias for specific tokens