root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 02:14:35 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

main: replace --no-special with --special (#7534)

Browse Source 
This also flips the default behavior of the output to not include control token by default.
This commit is contained in:
Brian 2024-05-27 00:10:17 +10:00 committed by GitHub
parent 32a28217f4
commit d298382ad9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 6 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
common/common.cpp
View File

@ -904,8 +904,8 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.interactive_specials = true;
return true;
}
if (arg == "--no-special") {
params.no_special = true;
if (arg == "--special") {
params.special = true;
return true;
}
if (arg == "--embedding") {
@ -1366,9 +1366,9 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
printf(" -h, --help show this help message and exit\n");
printf(" --version show version and build info\n");
printf(" -i, --interactive run in interactive mode\n");
printf(" --special special tokens output enabled\n");
printf(" --interactive-specials allow special tokens in user text, in interactive mode\n");
printf(" --interactive-first run in interactive mode and wait for input right away\n");
printf(" --no-special control tokens output disabled\n");
printf(" -cnv, --conversation run in conversation mode (does not print special tokens and suffix/prefix)\n");
printf(" -ins, --instruct run in instruction mode (use with Alpaca models)\n");
printf(" -cml, --chatml run in chatml mode (use with ChatML-compatible models)\n");

2
common/common.h
View File

@ -146,7 +146,7 @@ struct gpt_params {
bool use_color = false; // use color to distinguish generations and inputs
bool interactive = false; // interactive mode
bool interactive_specials = false; // whether to allow special tokens from user, during interactive mode
bool no_special = false; // disable control token output
bool special = false; // enable special token output
bool conversation = false; // conversation mode (does not print special tokens and suffix/prefix)
bool chatml = false; // chatml mode (used for models trained on chatml syntax)
bool prompt_cache_all = false; // save user input and generations to prompt cache

10
examples/main/main.cpp
View File

@ -740,16 +740,10 @@ int main(int argc, char ** argv) {
// display text
if (input_echo && display) {
for (auto id : embd) {
const std::string token_str = llama_token_to_piece(ctx, id);
const std::string token_str = llama_token_to_piece(ctx, id, params.special);
// Console/Stream Output
if (!llama_token_is_control(llama_get_model(ctx), id)) {
// Stream Output Token To Standard Output
fprintf(stdout, "%s", token_str.c_str());
} else if (!params.no_special && !params.conversation) {
// Stream Control Token To Standard Output Stream
fprintf(stdout, "%s", token_str.c_str());
}
fprintf(stdout, "%s", token_str.c_str());
// Record Displayed Tokens To Log
// Note: Generated tokens are created one by one hence this check