tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "10": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<s>",
  "chat_template": "{{ bos_token }}{% for message in messages %}{% if message['from'] == 'human' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + message['value'] | trim + '<|eot_id|>' }}{% elif message['from'] == 'gpt' %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' + message['value'] | trim + '<|eot_id|>' }}{% else %}{{ '<|start_header_id|>' + message['from'] + '<|end_header_id|>\n\n' + message['value'] | trim + '<|eot_id|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|im_end|>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<unk>"
}