Skip to content

main : restore old EOS behavior in interactive mode #2689

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 4 commits into from
Closed

main : restore old EOS behavior in interactive mode #2689

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8af1991
main : restore old EOS behavior in interactive mode
ggerganov Aug 21, 2023
e3da126
main : inject reverse prompt after EOS + update examples/chat.sh
ggerganov Aug 21, 2023
d3f5fbe
main : flush stdout
ggerganov Aug 21, 2023
977629a
Merge branch 'master' into fix-eos
ggerganov Aug 23, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions examples/chat.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@ cd ..
#
# "--keep 48" is based on the contents of prompts/chat-with-bob.txt
#
./main -m ./models/7B/ggml-model-q4_0.bin -c 512 -b 1024 -n 256 --keep 48 \
--repeat_penalty 1.0 --color -i \
-r "User:" -f prompts/chat-with-bob.txt
./main -m ./models/7B/ggml-model-q4_0.bin -c 512 -b 1024 -n -1 --keep 48 \
--repeat_penalty 1.0 --color \
-i --interactive-first \
-r "User:" --in-prefix " " \
-f prompts/chat-with-bob.txt
15 changes: 14 additions & 1 deletion examples/main/main.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -631,6 +631,16 @@ int main(int argc, char ** argv) {
llama_grammar_accept_token(ctx, grammar, id);
}

// replace end of text token with newline token and inject reverse prompt when in interactive mode
if (id == llama_token_eos() && params.interactive && !params.instruct && !params.input_prefix_bos) {
id = llama_token_nl();
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());
}
}

last_n_tokens.erase(last_n_tokens.begin());
last_n_tokens.push_back(id);
}
Expand Down Expand Up @@ -712,8 +722,8 @@ int main(int argc, char ** argv) {

is_interacting = true;
printf("\n");
console::set_display(console::user_input);
fflush(stdout);
console::set_display(console::user_input);
} else if (params.instruct) {
is_interacting = true;
}
Expand All @@ -722,6 +732,7 @@ int main(int argc, char ** argv) {
if (n_past > 0 && is_interacting) {
if (params.instruct) {
printf("\n> ");
fflush(stdout);
}

if (params.input_prefix_bos) {
Expand All @@ -732,6 +743,7 @@ int main(int argc, char ** argv) {
if (!params.input_prefix.empty()) {
buffer += params.input_prefix;
printf("%s", buffer.c_str());
fflush(stdout);
}

std::string line;
Expand All @@ -751,6 +763,7 @@ int main(int argc, char ** argv) {
if (!params.input_suffix.empty()) {
buffer += params.input_suffix;
printf("%s", params.input_suffix.c_str());
fflush(stdout);
}

// instruct mode: insert instruction prefix
Expand Down