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

android : minor

Browse source
This commit is contained in:
Georgi Gerganov 2024-03-10 22:02:44 +02:00 • committed by GitHub
parent 8d7ea8ec68
commit 13d21fa4bf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 20 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

46
examples/llama.android/app/src/main/cpp/llama-android.cpp
View file

@ -33,45 +33,38 @@ jclass la_int_var;
jmethodID la_int_var_value; jmethodID la_int_var_value;
jmethodID la_int_var_inc; jmethodID la_int_var_inc;
std::string cached_token_chars=""; std::string cached_token_chars;
bool is_valid_utf8(const char * string)
{ bool is_valid_utf8(const char * string) {
if (!string) if (!string) {
return true; return true;
}
const unsigned char * bytes = (const unsigned char *)string; const unsigned char * bytes = (const unsigned char *)string;
int num; int num;
while (*bytes != 0x00) while (*bytes != 0x00) {
{ if ((*bytes & 0x80) == 0x00) {
if ((*bytes & 0x80) == 0x00)
{
// U+0000 to U+007F // U+0000 to U+007F
num = 1; num = 1;
} } else if ((*bytes & 0xE0) == 0xC0) {
else if ((*bytes & 0xE0) == 0xC0)
{
// U+0080 to U+07FF // U+0080 to U+07FF
num = 2; num = 2;
} } else if ((*bytes & 0xF0) == 0xE0) {
else if ((*bytes & 0xF0) == 0xE0)
{
// U+0800 to U+FFFF // U+0800 to U+FFFF
num = 3; num = 3;
} } else if ((*bytes & 0xF8) == 0xF0) {
else if ((*bytes & 0xF8) == 0xF0)
{
// U+10000 to U+10FFFF // U+10000 to U+10FFFF
num = 4; num = 4;
} } else {
else
return false; return false;
}
bytes += 1; bytes += 1;
for (int i = 1; i < num; ++i) for (int i = 1; i < num; ++i) {
{ if ((*bytes & 0xC0) != 0x80) {
if ((*bytes & 0xC0) != 0x80)
return false; return false;
}
bytes += 1; bytes += 1;
} }
} }
@ -341,7 +334,7 @@ Java_com_example_llama_Llm_completion_1init(
jint n_len jint n_len
) { ) {
cached_token_chars = ""; cached_token_chars.clear();
const auto text = env->GetStringUTFChars(jtext, 0); const auto text = env->GetStringUTFChars(jtext, 0);
const auto context = reinterpret_cast<llama_context *>(context_pointer); const auto context = reinterpret_cast<llama_context *>(context_pointer);
@ -421,11 +414,12 @@ Java_com_example_llama_Llm_completion_1loop(
auto new_token_chars = llama_token_to_piece(context, new_token_id); auto new_token_chars = llama_token_to_piece(context, new_token_id);
cached_token_chars += new_token_chars; cached_token_chars += new_token_chars;
jstring new_token = nullptr; jstring new_token = nullptr;
if(is_valid_utf8(cached_token_chars.c_str())) { if (is_valid_utf8(cached_token_chars.c_str())) {
new_token = env->NewStringUTF(cached_token_chars.c_str()); new_token = env->NewStringUTF(cached_token_chars.c_str());
LOGi("cached: %s, new_token_chars: `%s`, id:%d", cached_token_chars.c_str(), new_token_chars.c_str(), new_token_id); LOGi("cached: %s, new_token_chars: `%s`, id: %d", cached_token_chars.c_str(), new_token_chars.c_str(), new_token_id);
cached_token_chars=""; cached_token_chars.clear();
} else { } else {
new_token = env->NewStringUTF(""); new_token = env->NewStringUTF("");
} }