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

Update llama.cpp

Browse source
This commit is contained in:
Georgi Gerganov 2023-07-28 21:09:19 +03:00 • committed by GitHub
parent efb5dac337
commit a8ee520eb8
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -1924,6 +1924,8 @@ struct llama_tokenizer {
if (token == vocab_.token_to_id.end()) { if (token == vocab_.token_to_id.end()) {
// output any symbols that did not form tokens as bytes. // output any symbols that did not form tokens as bytes.
for (int j = 0; j < (int) symbol.n; ++j) { for (int j = 0; j < (int) symbol.n; ++j) {
// NOTE: old version, before #2420 - not sure what are the implications of this
//llama_vocab::id token_id = static_cast<uint8_t>(symbol.text[j]) + 3;
llama_vocab::id token_id = vocab_.token_to_id.at(std::string(1, symbol.text[j])); llama_vocab::id token_id = vocab_.token_to_id.at(std::string(1, symbol.text[j]));
output.push_back(token_id); output.push_back(token_id);
} }