ollama/llm/patches/0005-default-pretokenizer.patch
Michael Yang 7bd7b02712 make patches git am-able
raw diffs can be applied using `git apply` but not with `git am`. git
patches, e.g. through `git format-patch` are both apply-able and am-able
2024-09-17 15:26:40 -07:00

44 lines
2.2 KiB
Diff

From b298ac8614d1e38da28f760eb1d2ae8af0fbbe62 Mon Sep 17 00:00:00 2001
From: Michael Yang <mxyng@pm.me>
Date: Mon, 16 Sep 2024 15:53:13 -0700
Subject: [PATCH] 05-default-pretokenizer.diff
---
src/llama.cpp | 14 +++-----------
1 file changed, 3 insertions(+), 11 deletions(-)
diff --git a/src/llama.cpp b/src/llama.cpp
index 926bb71a..d1e959fc 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -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;
- 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" ||
@@ -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__);
+ vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
}
} else if (vocab.type == LLAMA_VOCAB_TYPE_SPM) {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
--
2.46.0