Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Windows: convert prompt in system locale to UTF-8. #612

Closed
wants to merge 1 commit into from
Closed

Windows: convert prompt in system locale to UTF-8. #612

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 21 additions & 0 deletions examples/main/main.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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;
Expand All @@ -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";
Expand Down Expand Up @@ -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);

Expand Down