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
    },
    "128004": {
      "content": "<|finetune_right_pad_id|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128006": {
      "content": "<|start_header_id|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128007": {
      "content": "<|end_header_id|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128008": {
      "content": "<|eom_id|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128009": {
      "content": "<|eot_id|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128010": {
      "content": "<|python_tag|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|begin_of_text|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|end_of_text|>",
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 131072,
  "chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
  "pad_token": "<|finetune_right_pad_id|>",
  "padding_side": "left",
  "tokenizer_class": "PreTrainedTokenizerFast"
}