ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-06 06:20:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge mainline llama.cpp (#3)

Browse Source 
* Merging mainline - WIP

* Merging mainline - WIP

AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.

* Merging mainline - fix Metal

* Remove check

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-07-27 07:55:01 +02:00
committed by GitHub
parent 0684c3e9c7
commit 154e0d75fc
612 changed files with 50817 additions and 165936 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
examples/tokenize/tokenize.cpp
View File

@@ -29,7 +29,9 @@ static void print_usage_information(const char * argv0, FILE * stream) {
fprintf(stream, " -p PROMPT, --prompt PROMPT read prompt from the argument.\n");
fprintf(stream, " --stdin read prompt from standard input.\n");
fprintf(stream, " --no-bos do not ever add a BOS token to the prompt, even if normally the model uses a BOS token.\n");
fprintf(stream, " --no-parse-special do not parse control tokens.\n");
fprintf(stream, " --log-disable disable logs. Makes stderr quiet when loading the model.\n");
fprintf(stream, " --show-count print the total number of tokens.\n");
}
static void llama_log_callback_null(ggml_log_level level, const char * text, void * user_data) {
@@ -194,7 +196,9 @@ int main(int raw_argc, char ** raw_argv) {
// variables where to put any arguments we see.
bool printing_ids = false;
bool no_bos = false;
bool no_parse_special = false;
bool disable_logging = false;
bool show_token_count = false;
const char * model_path = NULL;
const char * prompt_path = NULL;
const char * prompt_arg = NULL;
@@ -227,6 +231,9 @@ int main(int raw_argc, char ** raw_argv) {
else if (arg == "--no-bos") {
no_bos = true;
}
else if (arg == "--no-parse-special") {
no_parse_special = true;
}
else if (arg == "-p" || arg == "--prompt") {
if (prompt_set) {
fprintf(stderr, "Error: -p or --prompt specified multiple times.\n");
@@ -249,6 +256,9 @@ int main(int raw_argc, char ** raw_argv) {
else if (arg == "--log-disable") {
disable_logging = true;
}
else if (arg == "--show-count") {
show_token_count = true;
}
else {
fprintf(stderr, "Error: unknown option '%s'\n", argv[iarg].c_str());
return 1;
@@ -354,9 +364,10 @@ int main(int raw_argc, char ** raw_argv) {
const bool model_wants_add_bos = llama_should_add_bos_token(model);
const bool add_bos = model_wants_add_bos && !no_bos;
const bool parse_special = !no_parse_special;
std::vector<llama_token> tokens;
tokens = ::llama_tokenize(model, prompt, add_bos, true);
tokens = ::llama_tokenize(model, prompt, add_bos, parse_special);
if (printing_ids) {
printf("[");
@@ -384,6 +395,9 @@ int main(int raw_argc, char ** raw_argv) {
printf("]\n");
}
if (show_token_count) {
printf("Total number of tokens: %ld\n", tokens.size());
}
// silence valgrind
llama_free(ctx);
llama_free_model(model);