Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-13 13:52:22 +01:00
Code Issues Packages Projects Releases Wiki Activity

server : respect --special cli arg (#8553)

Browse Source
This commit is contained in:
RunningLeon 2024-07-18 16:06:22 +08:00 committed by GitHub
parent e02b597be3
commit 3807c3de04
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@ -1182,7 +1182,7 @@ struct server_context {
bool process_token(completion_token_output & result, server_slot & slot) {
// remember which tokens were sampled - used for repetition penalties during sampling
const std::string token_str = llama_token_to_piece(ctx, result.tok, false);
const std::string token_str = llama_token_to_piece(ctx, result.tok, params.special);
slot.sampled = result.tok;
// search stop word and delete it