dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 02:24:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

feat: tokenization with llama.cpp (#4724)

Browse source 
feat: tokenization

Signed-off-by: shraddhazpy <shraddha@shraddhafive.in>
This commit is contained in:
Shraddha 2025-02-02 23:09:43 +05:30 • committed by GitHub
parent 1d6afbd65d
commit 03974a4dd4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 19 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

12
backend/cpp/llama/grpc-server.cpp
View file

@ -2542,6 +2542,18 @@ public:
return grpc::Status::OK;
}
grpc::Status TokenizeString(ServerContext* context, const backend::PredictOptions* request, backend::TokenizationResponse* response){
json data = parse_options(false, request, llama);
std::vector<llama_token> tokens = llama.tokenize(data["prompt"],false);
for (int i=0 ; i< tokens.size(); i++){
response->add_tokens(tokens[i]);
}
return grpc::Status::OK;
}
grpc::Status GetMetrics(ServerContext* context, const backend::MetricsRequest* request, backend::MetricsResponse* response) {
llama_client_slot* active_slot = llama.get_active_slot();