0cec062a63
* add glm edge chat model * use config partial_rotary_factor as rope ratio * support for glm edge model * vision model support * remove debug info * fix format * llava.cpp trailing whitespace * remove unused AutoTokenizer * Update src/llama.cpp for not contain <|end|> or </s> Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com> * add edge template * fix chat template * fix confict * fix confict * fix ci err * fix format err * fix template err * 9b hf chat support * format * format clip.cpp * fix format * Apply suggestions from code review * Apply suggestions from code review * Update examples/llava/clip.cpp * fix format * minor : style --------- Co-authored-by: liyuhang <yuhang.li@zhipuai.cn> Co-authored-by: piDack <pcdack@hotmail.co> Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com> Co-authored-by: liyuhang <yuhang.li@aminer.cn> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
53 lines
1.5 KiB
C++
53 lines
1.5 KiB
C++
#pragma once
|
|
|
|
#include <string>
|
|
#include <vector>
|
|
#include <cstdint>
|
|
|
|
enum llm_chat_template {
|
|
LLM_CHAT_TEMPLATE_CHATML,
|
|
LLM_CHAT_TEMPLATE_LLAMA_2,
|
|
LLM_CHAT_TEMPLATE_LLAMA_2_SYS,
|
|
LLM_CHAT_TEMPLATE_LLAMA_2_SYS_BOS,
|
|
LLM_CHAT_TEMPLATE_LLAMA_2_SYS_STRIP,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V1,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V3,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V3_TEKKEN,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V7,
|
|
LLM_CHAT_TEMPLATE_PHI_3,
|
|
LLM_CHAT_TEMPLATE_PHI_4,
|
|
LLM_CHAT_TEMPLATE_FALCON_3,
|
|
LLM_CHAT_TEMPLATE_ZEPHYR,
|
|
LLM_CHAT_TEMPLATE_MONARCH,
|
|
LLM_CHAT_TEMPLATE_GEMMA,
|
|
LLM_CHAT_TEMPLATE_ORION,
|
|
LLM_CHAT_TEMPLATE_OPENCHAT,
|
|
LLM_CHAT_TEMPLATE_VICUNA,
|
|
LLM_CHAT_TEMPLATE_VICUNA_ORCA,
|
|
LLM_CHAT_TEMPLATE_DEEPSEEK,
|
|
LLM_CHAT_TEMPLATE_DEEPSEEK_2,
|
|
LLM_CHAT_TEMPLATE_DEEPSEEK_3,
|
|
LLM_CHAT_TEMPLATE_COMMAND_R,
|
|
LLM_CHAT_TEMPLATE_LLAMA_3,
|
|
LLM_CHAT_TEMPLATE_CHATGML_3,
|
|
LLM_CHAT_TEMPLATE_CHATGML_4,
|
|
LLM_CHAT_TEMPLATE_GLMEDGE,
|
|
LLM_CHAT_TEMPLATE_MINICPM,
|
|
LLM_CHAT_TEMPLATE_EXAONE_3,
|
|
LLM_CHAT_TEMPLATE_RWKV_WORLD,
|
|
LLM_CHAT_TEMPLATE_GRANITE,
|
|
LLM_CHAT_TEMPLATE_GIGACHAT,
|
|
LLM_CHAT_TEMPLATE_MEGREZ,
|
|
LLM_CHAT_TEMPLATE_UNKNOWN,
|
|
};
|
|
|
|
struct llama_chat_message;
|
|
|
|
llm_chat_template llm_chat_template_from_str(const std::string & name);
|
|
|
|
llm_chat_template llm_chat_detect_template(const std::string & tmpl);
|
|
|
|
int32_t llm_chat_apply_template(
|
|
llm_chat_template tmpl,
|
|
const std::vector<const llama_chat_message *> & chat,
|
|
std::string & dest, bool add_ass);
|