vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : more tokenizer fixes (#2810)

Browse source 
* tests : write a Python tokenizer test (wip)

* llama : prefix input text for tokenization with whitespace

* llama : distinguish pieces from decoded text + fix detokenization

* common : add comments

* examples : no longer manually add leading space when tokenizing

* tests : use Python to generate tokenizer tests for C++

* tests : add option to tokenize text files

ggml-ci

* tests : add test-tokenizer-1.py

* llama.cpp : fix LF token

* hellaswag : move the concat space for clarity

* tests : add falcon tests (py + cpp, currently do not pass Unicode)

ggml-ci

* common : temporary separate llama_detokenize calls for SPM and BPE

---------

Co-authored-by: klosax <131523366+klosax@users.noreply.github.com>
This commit is contained in:
Georgi Gerganov 2023-08-27 14:19:19 +03:00 • committed by GitHub
parent 1591e2e590
commit edd4c14817
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
20 changed files with 671 additions and 224 deletions
Download patch file Download diff file Expand all files Collapse all files

14
tests/test-tokenizer-1.cpp
View file

@ -22,14 +22,6 @@ static std::string escape_whitespace(const std::string& text) {
return result;
}
static std::string unescape_whitespace(llama_context * ctx, const std::vector<llama_token> & tokens) {
std::string result;
for (size_t i = 0; i < tokens.size(); ++i) {
result += llama_token_to_str(ctx, tokens[i]);
}
return result;
}
int main(int argc, char **argv) {
if (argc < 2) {
fprintf(stderr, "Usage: %s <vocab-file>\n", argv[0]);
@ -72,13 +64,13 @@ int main(int argc, char **argv) {
const int n_vocab = llama_n_vocab(ctx);
for (int i = 0; i < n_vocab; ++i) {
std::string forward = llama_token_to_str(ctx, i);
std::string forward = llama_token_to_piece(ctx, i);
std::vector<llama_token> tokens = llama_tokenize(ctx, forward, false);
if (tokens.size() == 1) {
if (i != tokens[0]) {
std::string backward = llama_token_to_str(ctx, tokens[0]);
std::string backward = llama_token_to_piece(ctx, tokens[0]);
fprintf(stderr, "%s : error: token %d is string %s but bpe returns token %d %s\n",
__func__, i, llama_token_to_str(ctx, i).c_str(), tokens[0], backward.c_str());
__func__, i, llama_token_to_piece(ctx, i).c_str(), tokens[0], backward.c_str());
return 2;
}
}