tokenizer_config.json

{
  "added_tokens_decoder": {
    "128000": {
      "content": "<|begin_of_text|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128001": {
      "content": "<|end_of_text|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128002": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128003": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128004": {
      "content": "<|finetune_right_pad_id|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|begin_of_text|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|im_end|>",
  "extra_special_tokens": {},
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 65536,
  "pad_token": "<|end_of_text|>",
  "tokenizer_class": "PreTrainedTokenizerFast"
}