diff options
Diffstat (limited to 'llama.h')
| -rw-r--r-- | llama.h | 25 |
1 files changed, 25 insertions, 0 deletions
@@ -305,6 +305,12 @@ extern "C" { int32_t n_eval; }; + // used in chat template + typedef struct llama_chat_message { + const char * role; + const char * content; + } llama_chat_message; + // Helpers for getting default parameters LLAMA_API struct llama_model_params llama_model_default_params(void); LLAMA_API struct llama_context_params llama_context_default_params(void); @@ -699,6 +705,25 @@ extern "C" { char * buf, int32_t length); + /// Apply chat template. Inspired by hf apply_chat_template() on python. + /// Both "model" and "custom_template" are optional, but at least one is required. "custom_template" has higher precedence than "model" + /// NOTE: This function only support some known jinja templates. It is not a jinja parser. + /// @param tmpl A Jinja template to use for this chat. If this is nullptr, the model’s default chat template will be used instead. + /// @param chat Pointer to a list of multiple llama_chat_message + /// @param n_msg Number of llama_chat_message in this chat + /// @param add_ass Whether to end the prompt with the token(s) that indicate the start of an assistant message. + /// @param buf A buffer to hold the output formatted prompt. The recommended alloc size is 2 * (total number of characters of all messages) + /// @param length The size of the allocated buffer + /// @return The total number of bytes of the formatted prompt. If is it larger than the size of buffer, you may need to re-alloc it and then re-apply the template. + LLAMA_API int32_t llama_chat_apply_template( + const struct llama_model * model, + const char * tmpl, + const struct llama_chat_message * chat, + size_t n_msg, + bool add_ass, + char * buf, + int32_t length); + // // Grammar // |