llm: update llama.cpp commit to 8962422 (#6618)

This commit is contained in:
Jeffrey Morgan
2024-09-03 21:12:39 -04:00
committed by GitHub
parent f29b167e1a
commit 5e2653f9fe
7 changed files with 32 additions and 422 deletions

View File

@@ -1,8 +1,8 @@
diff --git a/src/llama.cpp b/src/llama.cpp
index a207451f..2ddf431d 100644
index 88355971..dd7d41ed 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -5347,16 +5347,7 @@ static void llm_load_vocab(
@@ -6083,16 +6083,7 @@ static void llm_load_vocab(
if (vocab.type == LLAMA_VOCAB_TYPE_BPE) {
vocab.tokenizer_add_space_prefix = false;
vocab.tokenizer_clean_spaces = true;
@@ -20,9 +20,9 @@ index a207451f..2ddf431d 100644
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;
@@ -6188,7 +6179,8 @@ static void llm_load_vocab(
tokenizer_pre == "exaone") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_EXAONE;
} 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__);