diff options
| author | Kyle Mistele <kyle@mistele.com> | 2024-04-24 05:15:29 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-24 13:15:29 +0300 |
| commit | 37246b1031b1680c0dcaf20aef736d6b446203fa (patch) | |
| tree | e058ba6529eb7436367f35d0d69e42684a8f431b /examples/server/server.cpp | |
| parent | 28103f4832e301a9c84d44ff0df9d75d46ab6c76 (diff) | |
common : revert showing control tokens by default for server (#6860)
* 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>
Diffstat (limited to 'examples/server/server.cpp')
| -rw-r--r-- | examples/server/server.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 68c63f9f..3acbd17d 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -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 |