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

18
common/common.cpp
View file

@ -12,6 +12,7 @@
#include <algorithm>
#include <cinttypes>
#include <climits>
#include <cmath>
#include <codecvt>
#include <cstdarg>
@ -23,10 +24,10 @@
#include <regex>
#include <sstream>
#include <string>
#include <thread>
#include <unordered_map>
#include <unordered_set>
#include <vector>
#include <thread>
#if defined(__APPLE__) && defined(__MACH__)
#include <sys/types.h>
@ -400,6 +401,21 @@ std::string common_params_get_system_info(const common_params & params) {
// String utils
//
std::string string_format(const char * fmt, ...) {
va_list ap;
va_list ap2;
va_start(ap, fmt);
va_copy(ap2, ap);
int size = vsnprintf(NULL, 0, fmt, ap);
GGML_ASSERT(size >= 0 && size < INT_MAX); // NOLINT
std::vector<char> buf(size + 1);
int size2 = vsnprintf(buf.data(), size + 1, fmt, ap2);
GGML_ASSERT(size2 == size);
va_end(ap2);
va_end(ap);
return std::string(buf.data(), size);
}
std::vector<std::string> string_split(std::string input, char separator) {
std::vector<std::string> parts;
size_t separator_pos = input.find(separator);