From f402d945ff203c1096a7394fd3f04991525b32f0 Mon Sep 17 00:00:00 2001 From: Edd <68678137+Erland366@users.noreply.github.com> Date: Wed, 23 Oct 2024 23:32:33 +0400 Subject: [PATCH] Fix/patch tokenizer (#1171) * fix: correct tokenizer handling in patch_sft_trainer_tokenizer * Revert "fix: correct tokenizer handling in patch_sft_trainer_tokenizer" This reverts commit 7a98e465cbd4f980c8b364b0396d44f2d052090f. * fix: correct condition for test_text assignment in patch_sft_trainer_tokenizer --- unsloth/tokenizer_utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/tokenizer_utils.py b/unsloth/tokenizer_utils.py index 1cad00d44d..4b9fd5e133 100644 --- a/unsloth/tokenizer_utils.py +++ b/unsloth/tokenizer_utils.py @@ -915,7 +915,7 @@ def patch_sft_trainer_tokenizer(): check_text = \ "\n"\ "if 'tokenizer' not in locals(): tokenizer = processing_class\n"\ - "test_text = dataset[0][dataset_text_field] if (formatting_func is not None and dataset_text_field is None) else formatting_func(dataset[0])[0]\n"\ + "test_text = dataset[0][dataset_text_field] if (formatting_func is None and dataset_text_field is not None) else formatting_func(dataset[0])[0]\n"\ "chat_template = getattr(tokenizer, 'chat_template', None)\n"\ "chat_template = '' if chat_template is None else chat_template\n"\ "has_bos_token_already = (test_text.startswith(tokenizer.bos_token) or tokenizer.bos_token in chat_template) "\