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

common : remove duplicate function llama_should_add_bos_token (#8778)

Browse source
This commit is contained in:
Zhenwei Jin 2024-08-15 15:23:23 +08:00 • committed by GitHub
parent 6bda7ce6c3
commit 4af8420afb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 26 additions and 40 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.h
View file

@ -380,10 +380,6 @@ std::string llama_detokenize(
const std::vector<llama_token> & tokens,
bool special = true);
// Uses the value from the model metadata if possible, otherwise
// defaults to true when model type is SPM, otherwise false.
bool llama_should_add_bos_token(const llama_model * model);
//
// Chat template utils
//