{ "vocab_size_target": 32768, "vocab_size_actual": 32768, "min_frequency": 2, "special_tokens": [ "<|bos|>", "<|eos|>", "<|pad|>", "<|unk|>", "<|system|>", "<|user|>", "<|assistant|>", "<|im_start|>", "<|im_end|>" ], "split_pattern": "'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)|\\s+" }