From ad3d38ad4dde514b842688d6fa184e085eaf5320 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Fri, 19 Jul 2024 01:06:41 -0700 Subject: [PATCH] Update tokenizer_utils.py --- unsloth/tokenizer_utils.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/unsloth/tokenizer_utils.py b/unsloth/tokenizer_utils.py index 7b88b0932f..07cd874125 100644 --- a/unsloth/tokenizer_utils.py +++ b/unsloth/tokenizer_utils.py @@ -41,14 +41,17 @@ IGNORED_TOKENIZER_CHECKING = frozenset(( )) -IGNORED_TOKENIZER_NAMES = frozenset(( +IGNORED_TOKENIZER_NAMES = [ "unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit", "unsloth/Mistral-Nemo-Instruct-2407", "mistralai/Mistral-Nemo-Instruct-2407", "unsloth/Mistral-Nemo-Base-2407-bnb-4bit", "unsloth/Mistral-Nemo-Base-2407", "mistralai/Mistral-Nemo-Base-2407", -)) +] +IGNORED_TOKENIZER_NAMES = frozenset( + [x.lower() for x in IGNORED_TOKENIZER_NAMES] +) # Check environments keynames = "\n" + "\n".join(os.environ.keys())