Skip to content

Commit

Permalink
main : add --conversation / -cnv flag (ggerganov#7108)
Browse files Browse the repository at this point in the history
  • Loading branch information
Dawid Potocki authored May 8, 2024
1 parent 465263d commit 83330d8
Show file tree
Hide file tree
Showing 3 changed files with 13 additions and 4 deletions.
5 changes: 5 additions & 0 deletions common/common.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -911,6 +911,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.instruct = true;
return true;
}
if (arg == "-cnv" || arg == "--conversation") {
params.conversation = true;
return true;
}
if (arg == "-cml" || arg == "--chatml") {
params.chatml = true;
return true;
Expand Down Expand Up @@ -1417,6 +1421,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" --version show version and build info\n");
printf(" -i, --interactive run 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");
printf(" -cml, --chatml run in chatml mode (use with ChatML-compatible models)\n");
printf(" --multiline-input allows you to write or paste multiple lines without ending each in '\\'\n");
Expand Down
1 change: 1 addition & 0 deletions common/common.h
Original file line number Diff line number Diff line change
Expand Up @@ -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 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
bool prompt_cache_ro = false; // open the prompt cache read-only and do not update it
Expand Down
11 changes: 7 additions & 4 deletions examples/main/main.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -362,6 +362,9 @@ int main(int argc, char ** argv) {
params.interactive_first = true;
params.antiprompt.emplace_back("<|im_start|>user\n");
}
else if (params.conversation) {
params.interactive_first = true;
}

// enable interactive mode if interactive start is specified
if (params.interactive_first) {
Expand Down Expand Up @@ -733,7 +736,7 @@ 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.conversation);
printf("%s", token_str.c_str());

if (embd.size() > 1) {
Expand Down Expand Up @@ -816,7 +819,7 @@ int main(int argc, char ** argv) {
if (n_past > 0 && is_interacting) {
LOG("waiting for user input\n");

if (params.instruct || params.chatml) {
if (params.conversation || params.instruct || params.chatml) {
printf("\n> ");
}

Expand All @@ -826,7 +829,7 @@ int main(int argc, char ** argv) {
}

std::string buffer;
if (!params.input_prefix.empty()) {
if (!params.input_prefix.empty() && !params.conversation) {
LOG("appending input prefix: '%s'\n", params.input_prefix.c_str());
printf("%s", params.input_prefix.c_str());
}
Expand All @@ -850,7 +853,7 @@ int main(int argc, char ** argv) {
// Entering a empty line lets the user pass control back
if (buffer.length() > 1) {
// append input suffix if any
if (!params.input_suffix.empty()) {
if (!params.input_suffix.empty() && !params.conversation) {
LOG("appending input suffix: '%s'\n", params.input_suffix.c_str());
printf("%s", params.input_suffix.c_str());
}
Expand Down

0 comments on commit 83330d8

Please sign in to comment.