extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-14 03:18:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-20 21:18:44 +03:00
parent d65a579a0a
commit e6c10cf3d5
28 changed files with 2521 additions and 1738 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/talk-llama/llama.h
View File

@ -1044,6 +1044,7 @@ extern "C" {
LLAMA_API bool llama_vocab_get_add_bos(const struct llama_vocab * vocab);
LLAMA_API bool llama_vocab_get_add_eos(const struct llama_vocab * vocab);
LLAMA_API bool llama_vocab_get_add_sep(const struct llama_vocab * vocab);
LLAMA_API llama_token llama_vocab_fim_pre(const struct llama_vocab * vocab);
LLAMA_API llama_token llama_vocab_fim_suf(const struct llama_vocab * vocab);
@ -1087,6 +1088,7 @@ 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
/// @return Returns INT32_MIN on overflow (e.g., tokenization result size exceeds int32_t limit)
/// @param add_special Allow to add BOS and EOS tokens if model is configured to do so.
/// @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.