tokenizer_config.json

{
  "model_type": "sentencepiece",
  "tokenizer_class": "PreTrainedTokenizerFast",
  "vocab_size": 8000,
  "model_max_length": 512,
  "bos_token": "<s>",
  "eos_token": "</s>",
  "unk_token": "<unk>",
  "pad_token": "<pad>",
  "sp_model_kwargs": {},
  "add_bos_token": false,
  "add_eos_token": false,
  "clean_up_tokenization_spaces": true,
  "legacy": true,
  "name_or_path": "khopilot/khmer-tokenizer-v7"
}