Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 13:28:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

Main+: optionally allow special tokens from user in interactive mode (#7097)

Browse Source 
@hanishkvc added a new `--interactive-specials` flag which would allow for inserting special tokens from user side into the embedding stream.
This commit is contained in:
HanishKVC 2024-05-10 15:51:58 +05:30 committed by GitHub
parent d11afd6652
commit f89fe2732c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
common/common.cpp
View File

@ -901,6 +901,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.interactive = true;
return true;
}
if (arg == "--interactive-specials") {
params.interactive_specials = true;
return true;
}
if (arg == "--embedding") {
params.embedding = true;
return true;
@ -1422,6 +1426,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
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(" --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(" -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");
@ -2652,6 +2657,7 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l
dump_string_yaml_multiline(stream, "in_suffix", params.input_prefix.c_str());
fprintf(stream, "instruct: %s # default: false\n", params.instruct ? "true" : "false");
fprintf(stream, "interactive: %s # default: false\n", params.interactive ? "true" : "false");
fprintf(stream, "interactive_specials: %s # default: false\n", params.interactive_specials ? "true" : "false");
fprintf(stream, "interactive_first: %s # default: false\n", params.interactive_first ? "true" : "false");
fprintf(stream, "keep: %d # default: 0\n", params.n_keep);
fprintf(stream, "logdir: %s # default: unset (no logging)\n", params.logdir.c_str());

1
common/common.h
View File

@ -140,6 +140,7 @@ struct gpt_params {
bool random_prompt = false; // do not randomize prompt if none provided
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 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

2
examples/main/main.cpp
View File

@ -879,7 +879,7 @@ int main(int argc, char ** argv) {
}
const auto line_pfx = ::llama_tokenize(ctx, params.input_prefix, false, true);
const auto line_inp = ::llama_tokenize(ctx, buffer, false, false);
const auto line_inp = ::llama_tokenize(ctx, buffer, false, params.interactive_specials);
const auto line_sfx = ::llama_tokenize(ctx, params.input_suffix, false, true);
LOG("input tokens: %s\n", LOG_TOKENS_TOSTR_PRETTY(ctx, line_inp).c_str());