tokenizer_config.json

{
  "add_bos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<|end_of_text|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<fim_prefix>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<fim_middle>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<fim_suffix>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<fim_pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "<filename>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<gh_stars>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "<issue_start>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "8": {
      "content": "<issue_comment>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "9": {
      "content": "<issue_closed>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "10": {
      "content": "<jupyter_start>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "11": {
      "content": "<jupyter_text>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "12": {
      "content": "<jupyter_code>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13": {
      "content": "<jupyter_output>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "14": {
      "content": "<empty_output>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "15": {
      "content": "<commit_before>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "16": {
      "content": "<commit_msg>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "17": {
      "content": "<commit_after>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "18": {
      "content": "<reponame>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49152": {
      "content": "<|start_of_role|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49153": {
      "content": "<|end_of_role|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49154": {
      "content": "<|tool_call|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49155": {
      "content": "<|start_of_cite|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49156": {
      "content": "<|end_of_cite|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49157": {
      "content": "<|start_of_plugin|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49158": {
      "content": "<|end_of_plugin|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|start_of_role|>",
    "<|end_of_role|>",
    "<|tool_call|>",
    "<|start_of_cite|>",
    "<|end_of_cite|>",
    "<|start_of_plugin|>",
    "<|end_of_plugin|>"
  ],
  "bos_token": "<|end_of_text|>",
  "chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' and loop.first %}{{ message['content'] }}{% elif message['role'] == 'user' %}{{ '### Instruction:\n' + message['content'] }}{% elif message['role'] == 'assistant' %}{{ '### Response:\n' + message['content'] + eos_token }}{% endif %}{% if not loop.last %}{{ '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n\n### Response:\n' }}{% endif %}",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|end_of_text|>",
  "errors": "replace",
  "extra_special_tokens": {},
  "model_max_length": 9223372036854775807,
  "pad_token": "<|end_of_text|>",
  "padding_side": "left",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|end_of_text|>",
  "vocab_size": 49152
}