PR #10853 server : add "tokens" output

server : add "tokens" output

ggerganov committed 275 days ago

server : update readme

ggerganov committed 275 days ago

server : return tokens ids only if requested

ggerganov committed 274 days ago

tests : improve "tokens" type check

ggerganov committed 274 days ago

server : remove "tokens" from the OAI endpoint

ggerganov committed 274 days ago

llama.cpp server : add "tokens" output #10853 Merged