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

llama : improve infill support and special token detection (#9798)

Browse source 
* llama : improve infill support

ggml-ci

* llama : add more FIM token strings

ggml-ci

* server : update prompt on slot restore (#9800)

* gguf : deprecate old FIM token KVs
This commit is contained in:
Georgi Gerganov 2024-10-12 08:21:51 +03:00 • committed by GitHub
parent 943d20b411
commit 11ac9800af
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 601 additions and 427 deletions
Download patch file Download diff file Expand all files Collapse all files

19
common/common.h
View file

@ -352,15 +352,28 @@ void common_init();
std::string common_params_get_system_info(const common_params & params);
bool parse_cpu_range(const std::string& range, bool(&boolmask)[GGML_MAX_N_THREADS]);
bool parse_cpu_mask(const std::string& mask, bool(&boolmask)[GGML_MAX_N_THREADS]);
void postprocess_cpu_params(cpu_params& cpuparams, const cpu_params* role_model = nullptr);
bool parse_cpu_range(const std::string & range, bool(&boolmask)[GGML_MAX_N_THREADS]);
bool parse_cpu_mask(const std::string & mask, bool(&boolmask)[GGML_MAX_N_THREADS]);
void postprocess_cpu_params(cpu_params & cpuparams, const cpu_params * role_model = nullptr);
bool set_process_priority(enum ggml_sched_priority prio);
//
// String utils
//
#ifdef __GNUC__
#ifdef __MINGW32__
#define LLAMA_COMMON_ATTRIBUTE_FORMAT(...) __attribute__((format(gnu_printf, __VA_ARGS__)))
#else
#define LLAMA_COMMON_ATTRIBUTE_FORMAT(...) __attribute__((format(printf, __VA_ARGS__)))
#endif
#else
#define LLAMA_COMMON_ATTRIBUTE_FORMAT(...)
#endif
LLAMA_COMMON_ATTRIBUTE_FORMAT(1, 2)
std::string string_format(const char * fmt, ...);
std::vector<std::string> string_split(std::string input, char separator);
std::string string_strip(const std::string & str);