vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into speculative-tree

Browse source
This commit is contained in:
Georgi Gerganov 2023-10-17 19:31:40 +03:00 • committed by GitHub
commit bd9451ca2a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
10 changed files with 385 additions and 90 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama.h
View file

@ -514,17 +514,20 @@ extern "C" {
// Tokenization
//
// Convert the provided text into tokens.
// The tokens pointer must be large enough to hold the resulting tokens.
// Returns the number of tokens on success, no more than n_max_tokens
// Returns a negative number on failure - the number of tokens that would have been returned
/// @details Convert the provided text into tokens.
/// @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_max_tokens
/// @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.
LLAMA_API int llama_tokenize(
const struct llama_model * model,
const char * text,
int text_len,
llama_token * tokens,
int n_max_tokens,
bool add_bos);
bool add_bos,
bool special);
// Token Id -> Piece.
// Uses the vocabulary in the provided context.