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

common : use common_ prefix for common library functions (#9805)

Browse source 
* common : use common_ prefix for common library functions

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Diego Devesa 2024-10-10 22:57:42 +02:00 • committed by GitHub
parent 0e9f760eb1
commit 7eee341bee
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
45 changed files with 1284 additions and 1284 deletions
Download patch file Download diff file Expand all files Collapse all files

10
tests/test-tokenizer-1-spm.cpp
View file

@ -66,9 +66,9 @@ int main(int argc, char ** argv) {
const int n_vocab = llama_n_vocab(model);
for (int i = 0; i < n_vocab; ++i) {
std::string str = llama_detokenize(ctx, std::vector<int>(1, i), true);
std::vector<llama_token> tokens = llama_tokenize(ctx, str, false, true);
std::string check = llama_detokenize(ctx, tokens);
std::string str = common_detokenize(ctx, std::vector<int>(1, i), true);
std::vector<llama_token> tokens = common_tokenize(ctx, str, false, true);
std::string check = common_detokenize(ctx, tokens);
if (check != str) {
fprintf(stderr, "%s : error: token %d detokenizes to '%s'(%zu) but tokenization of this detokenizes to '%s'(%zu)\n",
__func__, i, str.c_str(), str.length(), check.c_str(), check.length());
@ -93,8 +93,8 @@ int main(int argc, char ** argv) {
}
std::string str = unicode_cpt_to_utf8(cp);
std::vector<llama_token> tokens = llama_tokenize(ctx, str, false, true);
std::string check = llama_detokenize(ctx, tokens);
std::vector<llama_token> tokens = common_tokenize(ctx, str, false, true);
std::string check = common_detokenize(ctx, tokens);
if (cp != 9601 && str != check) {
fprintf(stderr, "error: codepoint 0x%x detokenizes to '%s'(%zu) instead of '%s'(%zu)\n",
cp, check.c_str(), check.length(), str.c_str(), str.length());