Unexpected tokenizer behavior difference from v4 to v5

[awni]

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('mlx-community/Llama-3.2-1B-Instruct-4bit')

text = tokenizer.decode([128000, 64, 1174, 65])
print(text)

For 4.57.3 you get <|begin_of_text|>a,b
For 5.0.0rc1 you get <|begin_of_text|>a ,b

Is it expected the behavior changed here?

Reproduction

Run the snippet above

Expected behavior

The two should have the same behavior right?