tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

BERT tokenizer fixes (#6498)

Browse Source 
Key changes:
* BERT conversion: fix abuse of LlamaHfVocab, do not set BOS or EOS
* Nomic Embed conversion: pad vocab instead of slicing embedding tensor
* llama_tokenize: handle added special tokens like HF does
This commit is contained in:
Jared Van Bortel
2024-04-09 13:44:08 -04:00
committed by GitHub
parent c4a3a4ff47
commit 1b67731e18
20 changed files with 221 additions and 194 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/embedding/embedding.cpp
View File

@ -123,10 +123,10 @@ int main(int argc, char ** argv) {
inputs.push_back(inp);
}
// add eos if not present
// add SEP if not present
for (auto & inp : inputs) {
if (inp.empty() || inp.back() != llama_token_eos(model)) {
inp.push_back(llama_token_eos(model));
if (inp.empty() || inp.back() != llama_token_sep(model)) {
inp.push_back(llama_token_sep(model));
}
}