Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-27 20:43:07 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama.android: add field formatChat to control whether to parse special tokens when send message (#11270)

Browse Source
This commit is contained in:
codezjx 2025-01-17 20:57:56 +08:00 committed by GitHub
parent 667d72846c
commit 3edfa7d375
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
examples/llama.android/llama/src/main/cpp/llama-android.cpp
View File

@ -347,6 +347,7 @@ Java_android_llama_cpp_LLamaAndroid_completion_1init(
jlong context_pointer,
jlong batch_pointer,
jstring jtext,
jboolean format_chat,
jint n_len
) {
@ -356,7 +357,8 @@ Java_android_llama_cpp_LLamaAndroid_completion_1init(
const auto context = reinterpret_cast<llama_context *>(context_pointer);
const auto batch = reinterpret_cast<llama_batch *>(batch_pointer);
const auto tokens_list = common_tokenize(context, text, 1);
bool parse_special = (format_chat == JNI_TRUE);
const auto tokens_list = common_tokenize(context, text, true, parse_special);
auto n_ctx = llama_n_ctx(context);
auto n_kv_req = tokens_list.size() + (n_len - tokens_list.size());
@ -368,7 +370,7 @@ Java_android_llama_cpp_LLamaAndroid_completion_1init(
}
for (auto id : tokens_list) {
LOGi("%s", common_token_to_piece(context, id).c_str());
LOGi("token: `%s`-> %d ", common_token_to_piece(context, id).c_str(), id);
}
common_batch_clear(*batch);

5
examples/llama.android/llama/src/main/java/android/llama/cpp/LLamaAndroid.kt
View File

@ -65,6 +65,7 @@ class LLamaAndroid {
context: Long,
batch: Long,
text: String,
formatChat: Boolean,
nLen: Int
): Int
@ -115,10 +116,10 @@ class LLamaAndroid {
}
}
fun send(message: String): Flow<String> = flow {
fun send(message: String, formatChat: Boolean = false): Flow<String> = flow {
when (val state = threadLocalState.get()) {
is State.Loaded -> {
val ncur = IntVar(completion_init(state.context, state.batch, message, nlen))
val ncur = IntVar(completion_init(state.context, state.batch, message, formatChat, nlen))
while (ncur.value <= nlen) {
val str = completion_loop(state.context, state.batch, state.sampler, nlen, ncur)
if (str == null) {