tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-20 06:36:48 -04:00
Code Issues 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 Mistele
2024-04-24 05:15:29 -05:00
committed by GitHub
parent 28103f4832
commit 37246b1031
3 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
common/common.h
View File

@@ -237,11 +237,12 @@ std::vector<llama_token> llama_tokenize(
bool add_special,
bool parse_special = false);
// tokenizes a token into a piece
// tokenizes a token into a piece, optionally renders special/control tokens
// should work similar to Python's `tokenizer.id_to_piece`
std::string llama_token_to_piece(
const struct llama_context * ctx,
llama_token token);
llama_token token,
bool special = true);
// TODO: these should be moved in llama.h C-style API under single `llama_detokenize` function
// that takes into account the tokenizer type and decides how to handle the leading space