Update llama.cpp submodule commit to d94c6e0c (#5805)

This commit is contained in:
Jeffrey Morgan
2024-07-22 12:42:00 -04:00
committed by GitHub
parent b3e5491e41
commit f8fedbda20
9 changed files with 366 additions and 81 deletions

View File

@@ -1,8 +1,8 @@
diff --git a/src/llama.cpp b/src/llama.cpp
index 2b9ace28..172640e2 100644
index 8fe51971..7113ba64 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -5357,16 +5357,7 @@ static void llm_load_vocab(
@@ -5433,16 +5433,7 @@ 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 2b9ace28..172640e2 100644
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
} else if (
tokenizer_pre == "llama3" ||
@@ -5439,7 +5430,8 @@ static void llm_load_vocab(
tokenizer_pre == "jais") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_JAIS;
@@ -5526,7 +5517,8 @@ static void llm_load_vocab(
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_SMOLLM;
vocab.tokenizer_clean_spaces = false;
} 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__);