mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-01 06:59:13 -04:00
android : fix utf8 decoding error (#5935)
* examples: fix utf8 decoding error some models have a tokenizer that decodes an id into an incomplete utf8 sequence, need to validate and wait for next token one example would be: https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat-GGUF/resolve/main/qwen1_5-1_8b-chat-q4_0.gguf and and an example of the token is 18137 * android : minor --------- Co-authored-by: zhangfuwen <zhangfuwen@foxmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
@@ -71,7 +71,7 @@ class Llm {
|
||||
batch: Long,
|
||||
nLen: Int,
|
||||
ncur: IntVar
|
||||
): String
|
||||
): String?
|
||||
|
||||
private external fun kv_cache_clear(context: Long)
|
||||
|
||||
@@ -115,7 +115,7 @@ class Llm {
|
||||
val ncur = IntVar(completion_init(state.context, state.batch, message, nlen))
|
||||
while (ncur.value <= nlen) {
|
||||
val str = completion_loop(state.context, state.batch, nlen, ncur)
|
||||
if (str.isEmpty()) {
|
||||
if (str == null) {
|
||||
break
|
||||
}
|
||||
emit(str)
|
||||
|
Reference in New Issue
Block a user