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

bugfix: centos 7, gcc (GCC) 11.2.1 20220127 (Red Hat 11.2.1-9)

Browse source 
std::string mesh up vocab.
This commit is contained in:
Lou Xiao 2023-03-19 17:03:31 +08:00
parent d7def1a752
commit 1d7e32bba7
No known key found for this signature in database
GPG key ID: 214E265F1716C5B0
1 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
main.cpp
View file

@ -144,15 +144,15 @@ bool llama_model_load(const std::string & fname, llama_model & model, gpt_vocab
// load vocab
{
std::string word;
for (int i = 0; i < model.hparams.n_vocab; i++) {
uint32_t len;
for (int i = 0; i < model.hparams.n_vocab; i++) {
fin.read((char *) &len, sizeof(len));
word.resize(len);
fin.read((char *) word.data(), len);
vocab.token_to_id[word] = i;
vocab.id_to_token[i] = word;
// force make a new std::string, some compiler may share inner data.
vocab.token_to_id[std::string(word.data(), len)] = i;
vocab.id_to_token[i] = std::string(word.data(), len);
//if (i < 30000) {
// fprintf(stderr, "%s: vocab[%d] = '%s'\n", __func__, i, word.c_str());