millaguie/llama.cpp
1
0 Fork 0
Code Issues Pull Requests Actions 32 Packages Projects Releases Wiki Activity

common : revert showing control tokens by default for server (#6860)

Browse Source 
* fix: revert showing control tokens by default

* feat: revert changes to default behavior of llama_token_to_piece; provide overridden declaration to receive "bool special" param to toggle showing control tokens

* feat: use the overridden declaration of llama_token_to_piece from common/common.cpp to specify "false" so that control tokens are not shown in chat completion responses"

* common : simplify

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Kyle MisteleandGeorgi Gerganov authored and GitHub committed 2024-04-24 13:15:29 +03:00
1 parent 28103f4832
commit 37246b1031
3 files changed
+7 -6
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

examples/server/server.cpp
+1 -1
View File
@@ -1117,7 +1117,7 @@ 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);
const std::string token_str = llama_token_to_piece(ctx, result.tok, false);
slot.sampled = result.tok;
// search stop word and delete it