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

Windows: convert prompt in system locale to UTF-8. Allows to use others languages without tambourine dancing...

Browse source
This commit is contained in:
Dmitriy Prikhodko 2023-03-30 04:22:45 +05:00
parent 9cbc404ba6
commit dc5adf173a
1 changed files with 21 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

21
examples/main/main.cpp
View file

@ -18,6 +18,10 @@
#include <signal.h>
#endif
#if defined (_WIN32)
#include <windows.h>
#endif
static console_state con_st;
static bool is_interacting = false;
@ -36,6 +40,18 @@ void sigint_handler(int signo) {
}
#endif
#if defined (_WIN32)
std::string promptconvert(const std::string str)
{
// Convert from current locale to UTF-8
wchar_t wstr[1024];
int wlen = MultiByteToWideChar(CP_ACP, 0, str.c_str(), str.length(), wstr, 1024);
char mbstr[2048];
int mblen = WideCharToMultiByte(CP_UTF8, 0, wstr, wlen, mbstr, 2048, 0, 0);
return std::string(mbstr, mblen);
}
#endif
int main(int argc, char ** argv) {
gpt_params params;
params.model = "models/llama-7B/ggml-model.bin";
@ -136,6 +152,11 @@ int main(int argc, char ** argv) {
// Add a space in front of the first character to match OG llama tokenizer behavior
params.prompt.insert(0, 1, ' ');
#if defined (_WIN32)
// Convert from current locale to UTF-8
params.prompt = promptconvert(params.prompt);
#endif
// tokenize the prompt
auto embd_inp = ::llama_tokenize(ctx, params.prompt, true);