root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

tokenize : add --no-parse-special option (#8423)

Browse Source 
This should allow more easily explaining
how parse_special affects tokenization.
This commit is contained in:
compilade 2024-07-11 03:41:48 -04:00 committed by GitHub
parent 7a221b672e
commit 9a55ffe6fb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
examples/tokenize/tokenize.cpp
View File

@ -29,6 +29,7 @@ static void print_usage_information(const char * argv0, FILE * stream) {
fprintf(stream, " -p PROMPT, --prompt PROMPT read prompt from the argument.\n"); fprintf(stream, " -p PROMPT, --prompt PROMPT read prompt from the argument.\n");
fprintf(stream, " --stdin read prompt from standard input.\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-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, " --log-disable disable logs. Makes stderr quiet when loading the model.\n");
fprintf(stream, " --show-count print the total number of tokens.\n"); fprintf(stream, " --show-count print the total number of tokens.\n");
} }
@ -195,6 +196,7 @@ int main(int raw_argc, char ** raw_argv) {
// variables where to put any arguments we see. // variables where to put any arguments we see.
bool printing_ids = false; bool printing_ids = false;
bool no_bos = false; bool no_bos = false;
bool no_parse_special = false;
bool disable_logging = false; bool disable_logging = false;
bool show_token_count = false; bool show_token_count = false;
const char * model_path = NULL; const char * model_path = NULL;
@ -229,6 +231,9 @@ int main(int raw_argc, char ** raw_argv) {
else if (arg == "--no-bos") { else if (arg == "--no-bos") {
no_bos = true; no_bos = true;
} }
else if (arg == "--no-parse-special") {
no_parse_special = true;
}
else if (arg == "-p" || arg == "--prompt") { else if (arg == "-p" || arg == "--prompt") {
if (prompt_set) { if (prompt_set) {
fprintf(stderr, "Error: -p or --prompt specified multiple times.\n"); fprintf(stderr, "Error: -p or --prompt specified multiple times.\n");
@ -359,9 +364,10 @@ int main(int raw_argc, char ** raw_argv) {
const bool model_wants_add_bos = llama_should_add_bos_token(model); const bool model_wants_add_bos = llama_should_add_bos_token(model);
const bool add_bos = model_wants_add_bos && !no_bos; const bool add_bos = model_wants_add_bos && !no_bos;
const bool parse_special = !no_parse_special;
std::vector<llama_token> tokens; 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) { if (printing_ids) {
printf("["); printf("[");