You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
44 lines
2.3 KiB
44 lines
2.3 KiB
3 weeks ago
|
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
||
|
|
From: Michael Yang <mxyng@pm.me>
|
||
|
|
Date: Mon, 16 Sep 2024 15:53:13 -0700
|
||
|
|
Subject: [PATCH] pretokenizer
|
||
|
|
|
||
|
|
allow for an unset pretokenizer with a warning in the
|
||
|
|
logs instead of throwing an error
|
||
|
|
---
|
||
|
|
src/llama-vocab.cpp | 14 +++-----------
|
||
|
|
1 file changed, 3 insertions(+), 11 deletions(-)
|
||
|
|
|
||
|
|
diff --git a/src/llama-vocab.cpp b/src/llama-vocab.cpp
|
||
|
|
index 9389ca80..806c1b3d 100644
|
||
|
|
--- a/src/llama-vocab.cpp
|
||
|
|
+++ b/src/llama-vocab.cpp
|
||
|
|
@@ -1503,16 +1503,7 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
|
||
|
|
if (type == LLAMA_VOCAB_TYPE_BPE) {
|
||
|
|
add_space_prefix = false;
|
||
|
|
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__);
|
||
|
|
- pre_type = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|
||
|
|
- } else if (tokenizer_pre == "default") {
|
||
|
|
+ if (tokenizer_pre == "default") {
|
||
|
|
pre_type = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|
||
|
|
} else if (
|
||
|
|
tokenizer_pre == "llama3" ||
|
||
|
|
@@ -1651,7 +1642,8 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
|
||
|
|
pre_type = LLAMA_VOCAB_PRE_TYPE_SEED_CODER;
|
||
|
|
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__);
|
||
|
|
+ pre_type = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|
||
|
|
}
|
||
|
|
} else if (type == LLAMA_VOCAB_TYPE_SPM) {
|
||
|
|
pre_type = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|