summaryrefslogtreecommitdiff
path: root/common/common.h
diff options
context:
space:
mode:
Diffstat (limited to 'common/common.h')
-rw-r--r--common/common.h5
1 files changed, 3 insertions, 2 deletions
diff --git a/common/common.h b/common/common.h
index cca44268..157b54a3 100644
--- a/common/common.h
+++ b/common/common.h
@@ -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