8000 We could use std::unordered_map over std::map by Fabio3rs · Pull Request #305 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

We could use std::unordered_map over std::map #305

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 7 commits into from
Mar 21, 2023
Merged

We could use std::unordered_map over std::map #305

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
25ef27c
Improve performance by changing std::map to std::unordered_map and st…
Fabio3rs Mar 19, 2023
78b964e
fix last commit on gpt_vocab_init add vocab.id_to_token.resize(vocab.…
Fabio3rs Mar 19, 2023
40ab486
Removed include <map>
Fabio3rs Mar 19, 2023
ef792ae
Merge unordered_map/vector changes with trunk updates
Fabio3rs Mar 20, 2023
3459653
Nest struct token score inside gpt_vocab
Fabio3rs Mar 21, 2023
a19aa63
renamed token to tok
Fabio3rs Mar 21, 2023
cfdf363
Resolved recent conflicts with master
Fabio3rs Mar 21, 2023
10000 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
Prev Previous commit
Next Next commit
renamed token to tok
  • Loading branch information
@Fabio3rs
Fabio3rs committed Mar 21, 2023
commit a19aa63ba29cc1c2b8370ad1d3993939afda13e8
8 changes: 4 additions & 4 deletions main.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -175,7 +175,7 @@ bool llama_model_load(const std::string & fname, llama_model & model, gpt_vocab
vocab.token_to_id[word] = i;

auto &tok_score = vocab.id_to_token[i];
tok_score.token = word;
tok_score.tok = word;
tok_score.score = score;

//if (i < 30000) {
Expand Down Expand Up @@ -896,7 +896,7 @@ int main(int argc, char ** argv) {
fprintf(stderr, "%s: prompt: '%s'\n", __func__, params.prompt.c_str());
fprintf(stderr, "%s: number of tokens in prompt = %zu\n", __func__, embd_inp.size());
for (int i = 0; i < (int) embd_inp.size(); i++) {
fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], vocab.id_to_token.at(embd_inp[i]).token.c_str());
fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], vocab.id_to_token.at(embd_inp[i]).tok.c_str());
}
fprintf(stderr, "\n");
if (params.interactive) {
Expand All @@ -918,7 +918,7 @@ int main(int argc, char ** argv) {
fprintf(stderr, "%s: reverse prompt: '%s'\n", __func__, params.antiprompt.at(apindex).c_str());
fprintf(stderr, "%s: number of tokens in reverse prompt = %zu\n", __func__, antiprompt_inp.size());
for (int i = 0; i < (int) antiprompt_inp.size(); i++) {
fprintf(stderr, "%6d -> '%s'\n", antiprompt_inp[i], vocab.id_to_token.at(antiprompt_inp[i]).token.c_str());
fprintf(stderr, "%6d -> '%s'\n", antiprompt_inp[i], vocab.id_to_token.at(antiprompt_inp[i]).tok.c_str());
}
fprintf(stderr, "\n");
}
Expand Down Expand Up @@ -1024,7 +1024,7 @@ int main(int argc, char ** argv) {
// display text
if (!input_noecho) {
for (auto id : embd) {
printf("%s", vocab.id_to_token[id].token.c_str());
printf("%s", vocab.id_to_token[id].tok.c_str());
}
fflush(stdout);
}
Expand Down
2 changes: 1 addition & 1 deletion quantize.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,7 +146,7 @@ bool llama_model_quantize(const std::string & fname_inp, const std::string & fna
vocab.token_to_id[word] = i;

auto &tok_score = vocab.id_to_token[i];
tok_score.token = word;
tok_score.tok = word;
tok_score.score = score;
}
}
Expand Down
2 changes: 1 addition & 1 deletion utils.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -444,7 +444,7 @@ bool gpt_vocab_init(const std::string & fname, gpt_vocab & vocab) {

vocab.id_to_token.resize(vocab.token_to_id.size());
for (const auto & kv : vocab.token_to_id) {
vocab.id_to_token[kv.second].token = kv.first;
vocab.id_to_token[kv.second].tok = kv.first;
}

printf("%s: vocab size = %d\n", __func__, (int) vocab.token_to_id.size());
Expand Down
2 changes: 1 addition & 1 deletion utils.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ struct gpt_vocab {
using token = std::string;

struct token_score {
token token;
token tok;
float score;
};

Expand Down
0