Skip to content

fixes infill incorrect tokenization #3508

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

Merged
merged 15 commits into from
Oct 10, 2023
Merged

fixes infill incorrect tokenization #3508

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
dfeda32
infill tokens correction
vvhg1 Oct 6, 2023
8bd24b2
Merge branch 'ggerganov:master' into master
vvhg1 Oct 6, 2023
6796e74
serverinfill tokens correction
vvhg1 Oct 6, 2023
377be2f
removing any leading whitespace from infill suffix and removing leead…
vvhg1 Oct 6, 2023
b4046aa
removing any leading whitespace from infill suffix and removing leead…
vvhg1 Oct 6, 2023
0526560
only rm when params.escape, rm space if possible which is added back …
vvhg1 Oct 7, 2023
63ba0b6
only rm when params.escape, rm space if possible which is added back …
vvhg1 Oct 7, 2023
003c15b
Revert "only rm when params.escape, rm space if possible which is add…
vvhg1 Oct 7, 2023
fc01dc0
Merge branch 'master' of github.com:ggerganov/llama.cpp
vvhg1 Oct 7, 2023
c3a7f84
fix interactive prompt escaping and fix server infill leading space h…
vvhg1 Oct 7, 2023
b1b6bef
rm unnecessary bool check
vvhg1 Oct 7, 2023
4a21468
Merge branch 'master' of github.com:ggerganov/llama.cpp
vvhg1 Oct 7, 2023
d9dae93
Merge branch 'master' of github.com:ggerganov/llama.cpp
vvhg1 Oct 8, 2023
141329f
Merge branch 'master' of github.com:ggerganov/llama.cpp
vvhg1 Oct 8, 2023
3517729
Merge branch 'master' of github.com:ggerganov/llama.cpp
vvhg1 Oct 9, 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
5 changes: 5 additions & 0 deletions examples/infill/infill.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -235,7 +235,12 @@ int main(int argc, char ** argv) {

std::vector<llama_token> embd_inp;
std::vector<llama_token> inp_pfx = ::llama_tokenize(ctx, params.input_prefix, false);
params.input_suffix.erase(0, params.input_suffix.find_first_not_of(" "));
std::vector<llama_token> inp_sfx = ::llama_tokenize(ctx, params.input_suffix, false);
const int space_token = 29871;
if (params.escape && inp_sfx.size() > 1 && inp_sfx[0] == space_token) {
Copy link
Member

@ggerganov ggerganov Oct 6, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we always want to remove the leading space, regardless if the params.escape is set or not:

Suggested change
if (params.escape && inp_sfx.size() > 1 && inp_sfx[0] == space_token) {
if (inp_sfx.size() > 1 && inp_sfx[0] == space_token) {

Copy link
Contributor Author

@vvhg1 vvhg1 Oct 7, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we need the params.escape check as only then we add an extra space to the suffix.

inp_sfx.erase(inp_sfx.begin());
}
inp_pfx.insert(inp_pfx.begin(), llama_token_prefix(ctx));
if (add_bos) {
inp_pfx.insert(inp_pfx.begin(), llama_token_bos(ctx));
Expand Down
5 changes: 5 additions & 0 deletions examples/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -344,8 +344,13 @@ struct llama_server_context

void loadInfill()
{
params.input_suffix.erase(0, params.input_suffix.find_first_not_of(" "));
auto prefix_tokens = tokenize(params.input_prefix, false);
auto suffix_tokens = tokenize(params.input_suffix, false);
const int space_token = 29871;
if (params.escape && suffix_tokens.size() > 1 && suffix_tokens[0] == space_token) {
suffix_tokens.erase(suffix_tokens.begin());
}
prefix_tokens.insert(prefix_tokens.begin(), llama_token_prefix(ctx));
prefix_tokens.insert(prefix_tokens.begin(), llama_token_bos(ctx)); // always add BOS
prefix_tokens.insert(prefix_tokens.end(), llama_token_suffix(ctx));
Expand Down