CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-29 08:41:22 +00:00
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
1 changed files with 1 additions and 1 deletions
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) { bool process_token(completion_token_output & result, server_slot & slot) {
// remember which tokens were sampled - used for repetition penalties during sampling // 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; slot.sampled = result.tok;
// search stop word and delete it // search stop word and delete it