admin/ollama
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ollama source for Momentry Core verification

Browse Source
This commit is contained in:
Accusys
2026-05-22 17:19:10 +08:00
commit 0b31ff9135
2020 changed files with 1413145 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
llama/patches/0002-pretokenizer.patch Normal file
View File

@@ -0,0 +1,43 @@
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 7b01a2edf..63250cdf1 100644
--- a/src/llama-vocab.cpp
+++ b/src/llama-vocab.cpp
@@ -1825,16 +1825,7 @@ 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" ||
@@ -2015,7 +2006,8 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
pre_type = LLAMA_VOCAB_PRE_TYPE_MINIMAX_M2;
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;