Skip to content

vocab : fix ugm tokenizer precision #13743

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 1 commit into from
May 24, 2025
Merged

vocab : fix ugm tokenizer precision #13743

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 4 additions & 4 deletions src/llama-vocab.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -835,7 +835,7 @@ struct llm_tokenizer_ugm_session {
}

// initialize score_sum to -FLT_MAX so it will be always lower than sums of token scores
std::vector<struct best_tokenization> tokenization_results(input_len + 1, {vocab.token_unk(), 0, -FLT_MAX});
std::vector<struct best_tokenization> tokenization_results(input_len + 1, {vocab.token_unk(), 0, -DBL_MAX});
// at the beginning tokenization score is zero
tokenization_results[0] = { vocab.token_unk(), 0, 0 };

Expand Down Expand Up @@ -867,7 +867,7 @@ struct llm_tokenizer_ugm_session {
const double challenger_score = current_best.score_sum + token_score;
struct best_tokenization & current_champ = tokenization_results[prefix_offset];
if (challenger_score > current_champ.score_sum) {
struct best_tokenization challenger = { token_id, input_offset, (float) challenger_score };
struct best_tokenization challenger = { token_id, input_offset, challenger_score };
current_champ = challenger;
}
}
Expand All @@ -881,7 +881,7 @@ struct llm_tokenizer_ugm_session {
prefix_offset = input_offset + n_utf8_code_units;
struct best_tokenization & current_champ = tokenization_results[prefix_offset];
if (challenger_score > current_champ.score_sum) {
struct best_tokenization challenger = { vocab.token_unk(), input_offset, (float) challenger_score };
struct best_tokenization challenger = { vocab.token_unk(), input_offset, challenger_score };
current_champ = challenger;
}
}
Expand Down Expand Up @@ -1007,7 +1007,7 @@ struct llm_tokenizer_ugm_session {
struct best_tokenization {
llama_token token_id;
size_t input_offset;
float score_sum;
double score_sum;
};

struct normalization_result normalize_prefix(const std::string & input, size_t input_offset) {
Expand Down
Loading