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 : add --in-prefix-bos to prefix BOS to user inputs; keep EOS (#2304)

Browse Source 
* add `--in-prefix-bos` to prefix BOS to user inputs; keep EOS

The BOS precedes the string specified by `--in-prefix`.
Model generated EOS is now kept in the context.

It provides a way to strictly following the prompt format used in
Llama-2-chat.

The EOS handling also benefits some existing finetunes that uses
EOS to mark the end of turn.

* examples/common: move input_prefix_bos to other bools
This commit is contained in:
Xiao-Yong Jin 2023-07-25 07:19:11 -05:00 committed by GitHub
parent 1fed755b1f
commit 0c06204fb3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 34 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
examples/common.cpp
View File

@ -432,6 +432,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
exit(0);
} else if (arg == "--random-prompt") {
params.random_prompt = true;
} else if (arg == "--in-prefix-bos") {
params.input_prefix_bos = true;
} else if (arg == "--in-prefix") {
if (++i >= argc) {
invalid_param = true;
@ -517,6 +519,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stdout, " not supported with --interactive or other interactive options\n");
fprintf(stdout, " --prompt-cache-ro if specified, uses the prompt cache but does not update it.\n");
fprintf(stdout, " --random-prompt start with a randomized prompt.\n");
fprintf(stdout, " --in-prefix-bos prefix BOS to user inputs, preceding the `--in-prefix` string\n");
fprintf(stdout, " --in-prefix STRING string to prefix user inputs with (default: empty)\n");
fprintf(stdout, " --in-suffix STRING string to suffix after user inputs with (default: empty)\n");
fprintf(stdout, " -f FNAME, --file FNAME\n");

1
examples/common.h
View File

@ -82,6 +82,7 @@ struct gpt_params {
bool interactive_first = false; // wait for user input immediately
bool multiline_input = false; // reverse the usage of `\`
bool input_prefix_bos = false; // prefix BOS to user inputs, preceding input_prefix
bool instruct = false; // instruction mode (used for Alpaca models)
bool penalize_nl = true; // consider newlines as a repeatable token
bool perplexity = false; // compute perplexity over the prompt

47
examples/main/main.cpp
View File

@ -325,6 +325,10 @@ int main(int argc, char ** argv) {
}
}
if (params.input_prefix_bos) {
fprintf(stderr, "Input prefix with BOS\n");
}
if (!params.input_prefix.empty()) {
fprintf(stderr, "Input prefix: '%s'\n", params.input_prefix.c_str());
}
@ -633,16 +637,6 @@ int main(int argc, char ** argv) {
last_n_tokens.push_back(id);
}
// replace end of text token with newline token when in interactive mode
if (id == llama_token_eos() && params.interactive && !params.instruct) {
id = llama_token_newline.front();
if (params.antiprompt.size() != 0) {
// tokenize and inject first reverse prompt
const auto first_antiprompt = ::llama_tokenize(ctx, params.antiprompt.front(), false);
embd_inp.insert(embd_inp.end(), first_antiprompt.begin(), first_antiprompt.end());
}
}
// add it to the context
embd.push_back(id);
@ -708,11 +702,34 @@ int main(int argc, char ** argv) {
}
}
// deal with end of text token in interactive mode
if (last_n_tokens.back() == llama_token_eos()) {
if (params.interactive) {
if (params.antiprompt.size() != 0) {
// tokenize and inject first reverse prompt
const auto first_antiprompt = ::llama_tokenize(ctx, params.antiprompt.front(), false);
embd_inp.insert(embd_inp.end(), first_antiprompt.begin(), first_antiprompt.end());
is_antiprompt = true;
}
is_interacting = true;
printf("\n");
console_set_color(con_st, CONSOLE_COLOR_USER_INPUT);
fflush(stdout);
} else if (params.instruct) {
is_interacting = true;
}
}
if (n_past > 0 && is_interacting) {
if (params.instruct) {
printf("\n> ");
}
if (params.input_prefix_bos) {
embd_inp.push_back(llama_token_bos());
}
std::string buffer;
if (!params.input_prefix.empty()) {
buffer += params.input_prefix;
@ -776,13 +793,9 @@ int main(int argc, char ** argv) {
}
// end of text token
if (!embd.empty() && embd.back() == llama_token_eos()) {
if (params.instruct) {
is_interacting = true;
} else {
fprintf(stderr, " [end of text]\n");
break;
}
if (!embd.empty() && embd.back() == llama_token_eos() && !(params.instruct || params.interactive)) {
fprintf(stderr, " [end of text]\n");
break;
}
// In interactive mode, respect the maximum number of tokens and drop back to user input when reached.