matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-11 16:26:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama: update vendored code to commit 46e3556 (#8308)

Browse Source
This commit is contained in:
Jeffrey Morgan
2025-01-08 11:22:01 -08:00
committed by GitHub
parent 57f038ec7b
commit 1deafd8254
305 changed files with 16048 additions and 12926 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
llama/unicode.h vendored
View File

@@ -1,5 +1,5 @@
/**
* llama.cpp - commit ba1cb19cdd0d92e012e0f6e009e0620f854b6afd - do not edit this file
* llama.cpp - commit 46e3556e01b824e52395fb050b29804b6cff2a7c - do not edit this file
*
* MIT License
*
@@ -30,9 +30,7 @@
#include <string>
#include <vector>
// TODO: prefix all symbols with "llama_"
struct codepoint_flags {
struct unicode_cpt_flags {
enum {
UNDEFINED = 0x0001,
NUMBER = 0x0002, // regex: \p{N}
@@ -61,7 +59,7 @@ struct codepoint_flags {
uint16_t is_nfd : 1;
// decode from uint16
inline codepoint_flags(const uint16_t flags=0) {
inline unicode_cpt_flags(const uint16_t flags = 0) {
*reinterpret_cast<uint16_t*>(this) = flags;
}
@@ -76,18 +74,19 @@ struct codepoint_flags {
size_t unicode_len_utf8(char src);
std::string unicode_cpt_to_utf8(uint32_t cp);
uint32_t unicode_cpt_from_utf8(const std::string & utf8, size_t & offset);
std::string unicode_cpt_to_utf8 (uint32_t cpt);
uint32_t unicode_cpt_from_utf8(const std::string & utf8, size_t & offset);
std::vector<uint32_t> unicode_cpts_from_utf8(const std::string & utf8);
std::vector<uint32_t> unicode_cpts_normalize_nfd(const std::vector<uint32_t> & cpts);
codepoint_flags unicode_cpt_flags(const uint32_t cp);
codepoint_flags unicode_cpt_flags(const std::string & utf8);
unicode_cpt_flags unicode_cpt_flags_from_cpt (uint32_t cpt);
unicode_cpt_flags unicode_cpt_flags_from_utf8(const std::string & utf8);
std::string unicode_byte_to_utf8(uint8_t byte);
uint8_t unicode_utf8_to_byte(const std::string & utf8);
uint8_t unicode_utf8_to_byte(const std::string & utf8);
uint32_t unicode_tolower(uint32_t cp);
uint32_t unicode_tolower(uint32_t cpt);
std::vector<std::string> unicode_regex_split(const std::string & text, const std::vector<std::string> & regex_exprs);