32 lines
1.9 KiB
Diff
32 lines
1.9 KiB
Diff
diff --git a/src/llama.cpp b/src/llama.cpp
|
|
index a207451f..2ddf431d 100644
|
|
--- a/src/llama.cpp
|
|
+++ b/src/llama.cpp
|
|
@@ -5347,16 +5347,7 @@ static void llm_load_vocab(
|
|
if (vocab.type == LLAMA_VOCAB_TYPE_BPE) {
|
|
vocab.tokenizer_add_space_prefix = false;
|
|
vocab.tokenizer_clean_spaces = true;
|
|
- if (tokenizer_pre.empty()) {
|
|
- LLAMA_LOG_WARN("%s: missing pre-tokenizer type, using: 'default'\n", __func__);
|
|
- LLAMA_LOG_WARN("%s: \n", __func__);
|
|
- LLAMA_LOG_WARN("%s: ************************************ \n", __func__);
|
|
- LLAMA_LOG_WARN("%s: GENERATION QUALITY WILL BE DEGRADED! \n", __func__);
|
|
- LLAMA_LOG_WARN("%s: CONSIDER REGENERATING THE MODEL \n", __func__);
|
|
- LLAMA_LOG_WARN("%s: ************************************ \n", __func__);
|
|
- LLAMA_LOG_WARN("%s: \n", __func__);
|
|
- vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|
|
- } else if (tokenizer_pre == "default") {
|
|
+ if (tokenizer_pre == "default") {
|
|
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|
|
} else if (
|
|
tokenizer_pre == "llama3" ||
|
|
@@ -5443,7 +5434,8 @@ static void llm_load_vocab(
|
|
tokenizer_pre == "codeshell") {
|
|
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_CODESHELL;
|
|
} else {
|
|
- throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
|
|
+ LLAMA_LOG_WARN("%s: missing or unrecognized pre-tokenizer type, using: 'default'\n", __func__);
|
|
+ vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|
|
}
|
|
} else if (vocab.type == LLAMA_VOCAB_TYPE_SPM) {
|
|
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|