diff --git a/.github/workflows/python-lint.yml b/.github/workflows/python-lint.yml
index f4ae65495..c07b9aa83 100644
--- a/.github/workflows/python-lint.yml
+++ b/.github/workflows/python-lint.yml
@@ -20,5 +20,5 @@ jobs:
       - name: flake8 Lint
         uses: py-actions/flake8@v2
         with:
-            ignore: "E203,E211,E221,E225,E231,E241,E251,E261,E266,E501,E701,E704,W503"
+            ignore: "E203,E211,E221,E222,E225,E231,E241,E251,E261,E266,E501,E701,E704,W503"
             exclude: "examples/*,examples/*/**,*/**/__init__.py"
diff --git a/convert-hf-to-gguf.py b/convert-hf-to-gguf.py
index 06fa9996d..af698a23a 100755
--- a/convert-hf-to-gguf.py
+++ b/convert-hf-to-gguf.py
@@ -406,7 +406,7 @@ class Model(ABC):
                 res = "deepseek-coder"
 
         if res is None:
-            raise NotImplementedError(f"BPE pre-tokenizer was not recognized - update get_vocab_base_pre()")
+            raise NotImplementedError("BPE pre-tokenizer was not recognized - update get_vocab_base_pre()")
 
         return res
 
diff --git a/llama.cpp b/llama.cpp
index d8e691c18..923a49877 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -12033,6 +12033,8 @@ struct llm_tokenizer_bpe {
                         word_collection = unicode_regex_split(text, {
                             // TODO: ??????????????
                             //"(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+
+
+                            // TODO: this is wrong - need to use ReFlex and update unicode.cpp to support the regex above
                             "\\p{P}+",
                             "'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)",
                             "\\p{N}+",