summaryrefslogtreecommitdiff
path: root/llama.h
diff options
context:
space:
mode:
Diffstat (limited to 'llama.h')
-rw-r--r--llama.h10
1 files changed, 6 insertions, 4 deletions
diff --git a/llama.h b/llama.h
index 6a5bbe26..b770a275 100644
--- a/llama.h
+++ b/llama.h
@@ -786,6 +786,8 @@ extern "C" {
// Special tokens
LLAMA_API llama_token llama_token_bos(const struct llama_model * model); // beginning-of-sentence
LLAMA_API llama_token llama_token_eos(const struct llama_model * model); // end-of-sentence
+ LLAMA_API llama_token llama_token_cls(const struct llama_model * model); // classification
+ LLAMA_API llama_token llama_token_sep(const struct llama_model * model); // sentence separator
LLAMA_API llama_token llama_token_nl (const struct llama_model * model); // next-line
// Returns -1 if unknown, 1 for true or 0 for false.
@@ -808,16 +810,16 @@ extern "C" {
/// @param tokens The tokens pointer must be large enough to hold the resulting tokens.
/// @return Returns the number of tokens on success, no more than n_tokens_max
/// @return Returns a negative number on failure - the number of tokens that would have been returned
- /// @param special Allow tokenizing special and/or control tokens which otherwise are not exposed and treated as plaintext.
- /// Does not insert a leading space.
+ /// @param parse_special Allow tokenizing special and/or control tokens which otherwise are not exposed and treated
+ /// as plaintext. Does not insert a leading space.
LLAMA_API int32_t llama_tokenize(
const struct llama_model * model,
const char * text,
int32_t text_len,
llama_token * tokens,
int32_t n_tokens_max,
- bool add_bos,
- bool special);
+ bool add_special,
+ bool parse_special);
// Token Id -> Piece.
// Uses the vocabulary in the provided context.