mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 02:44:36 +00:00
main : don't print special tokens with --grammar (#6923)
* main : don't print special tokens with --grammar The CLI interface was recently changed to print special control tokens like the </s> stop message one. This token shouldn't be printed if the grammar flag was passed, unless the grammar specifies it, because that breaks shell-scriptability. * main: use seperate stream for control characters * main: use dprintf and add --ctrl-token-no-out and --ctrl-token-fd-out * main: dprintf isn't part of the IEEE POSIX standard. Just use write(). * main: remove --ctrl-token-fd-out in favor for fcntl() based detection * common.cpp: accidentally removed --interactive-first * main: only merge stdout and control token if not in conversation or grammar mode * main: rejig control token descriptor handling * main: must check pipe status on very top of program * main: renamed --no-special from --ctrl-token-no-out and other refactoring * main: refactor ctrl_token_no_out --> no_special * llama: rename llama_token_is_control_token() to llama_token_is_control() * main: remove special token file descriptor feature (#5) --------- Co-authored-by: Brian <mofosyne@gmail.com>
This commit is contained in:
parent
faa0e6979a
commit
00c6390793
@ -904,6 +904,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
|
|||||||
params.interactive_specials = true;
|
params.interactive_specials = true;
|
||||||
return true;
|
return true;
|
||||||
}
|
}
|
||||||
|
if (arg == "--no-special") {
|
||||||
|
params.no_special = true;
|
||||||
|
return true;
|
||||||
|
}
|
||||||
if (arg == "--embedding") {
|
if (arg == "--embedding") {
|
||||||
params.embedding = true;
|
params.embedding = true;
|
||||||
return true;
|
return true;
|
||||||
@ -1364,6 +1368,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
|
|||||||
printf(" -i, --interactive run in interactive mode\n");
|
printf(" -i, --interactive run in interactive mode\n");
|
||||||
printf(" --interactive-specials allow special tokens in user text, in interactive mode\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(" --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(" -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(" -ins, --instruct run in instruction mode (use with Alpaca models)\n");
|
||||||
printf(" -cml, --chatml run in chatml mode (use with ChatML-compatible models)\n");
|
printf(" -cml, --chatml run in chatml mode (use with ChatML-compatible models)\n");
|
||||||
|
@ -146,6 +146,7 @@ struct gpt_params {
|
|||||||
bool use_color = false; // use color to distinguish generations and inputs
|
bool use_color = false; // use color to distinguish generations and inputs
|
||||||
bool interactive = false; // interactive mode
|
bool interactive = false; // interactive mode
|
||||||
bool interactive_specials = false; // whether to allow special tokens from user, during 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 conversation = false; // conversation mode (does not print special tokens and suffix/prefix)
|
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 chatml = false; // chatml mode (used for models trained on chatml syntax)
|
||||||
bool prompt_cache_all = false; // save user input and generations to prompt cache
|
bool prompt_cache_all = false; // save user input and generations to prompt cache
|
||||||
|
@ -740,18 +740,32 @@ int main(int argc, char ** argv) {
|
|||||||
// display text
|
// display text
|
||||||
if (input_echo && display) {
|
if (input_echo && display) {
|
||||||
for (auto id : embd) {
|
for (auto id : embd) {
|
||||||
const std::string token_str = llama_token_to_piece(ctx, id, !params.conversation);
|
const std::string token_str = llama_token_to_piece(ctx, id);
|
||||||
printf("%s", token_str.c_str());
|
|
||||||
|
|
||||||
|
// 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());
|
||||||
|
}
|
||||||
|
|
||||||
|
// Record Displayed Tokens To Log
|
||||||
|
// Note: Generated tokens are created one by one hence this check
|
||||||
if (embd.size() > 1) {
|
if (embd.size() > 1) {
|
||||||
|
// Incoming Requested Tokens
|
||||||
input_tokens.push_back(id);
|
input_tokens.push_back(id);
|
||||||
} else {
|
} else {
|
||||||
|
// Outgoing Generated Tokens
|
||||||
output_tokens.push_back(id);
|
output_tokens.push_back(id);
|
||||||
output_ss << token_str;
|
output_ss << token_str;
|
||||||
}
|
}
|
||||||
}
|
|
||||||
fflush(stdout);
|
fflush(stdout);
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
|
||||||
// reset color to default if there is no pending user input
|
// reset color to default if there is no pending user input
|
||||||
if (input_echo && (int) embd_inp.size() == n_consumed) {
|
if (input_echo && (int) embd_inp.size() == n_consumed) {
|
||||||
console::set_display(console::reset);
|
console::set_display(console::reset);
|
||||||
|
@ -17861,6 +17861,10 @@ bool llama_token_is_eog(const struct llama_model * model, llama_token token) {
|
|||||||
);
|
);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
bool llama_token_is_control(const struct llama_model * model, llama_token token) {
|
||||||
|
return llama_is_control_token(model->vocab, token);
|
||||||
|
}
|
||||||
|
|
||||||
llama_token llama_token_bos(const struct llama_model * model) {
|
llama_token llama_token_bos(const struct llama_model * model) {
|
||||||
return model->vocab.special_bos_id;
|
return model->vocab.special_bos_id;
|
||||||
}
|
}
|
||||||
|
3
llama.h
3
llama.h
@ -823,6 +823,9 @@ extern "C" {
|
|||||||
// Check if the token is supposed to end generation (end-of-generation, eg. EOS, EOT, etc.)
|
// Check if the token is supposed to end generation (end-of-generation, eg. EOS, EOT, etc.)
|
||||||
LLAMA_API bool llama_token_is_eog(const struct llama_model * model, llama_token token);
|
LLAMA_API bool llama_token_is_eog(const struct llama_model * model, llama_token token);
|
||||||
|
|
||||||
|
// Identify if Token Id is a control token or a render-able token
|
||||||
|
LLAMA_API bool llama_token_is_control(const struct llama_model * model, llama_token token);
|
||||||
|
|
||||||
// Special tokens
|
// Special tokens
|
||||||
LLAMA_API llama_token llama_token_bos(const struct llama_model * model); // beginning-of-sentence
|
LLAMA_API llama_token llama_token_bos(const struct llama_model * model); // beginning-of-sentence
|
||||||
LLAMA_API llama_token llama_token_eos(const struct llama_model * model); // end-of-sentence
|
LLAMA_API llama_token llama_token_eos(const struct llama_model * model); // end-of-sentence
|
||||||
|
Loading…
Reference in New Issue
Block a user