tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "200000": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200001": {
      "content": "<fim_prefix>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200002": {
      "content": "<fim_middle>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200003": {
      "content": "<fim_suffix>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200004": {
      "content": "<fim_pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200005": {
      "content": "<reponame>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200006": {
      "content": "<filename>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200007": {
      "content": "<gh_stars>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200008": {
      "content": "<issue_start>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200009": {
      "content": "<issue_comment>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200010": {
      "content": "<issue_closed>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200011": {
      "content": "<jupyter_start>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200012": {
      "content": "<jupyter_text>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200013": {
      "content": "<jupyter_code>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200014": {
      "content": "<jupyter_output>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200015": {
      "content": "<empty_output>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200016": {
      "content": "<commit_before>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200017": {
      "content": "<commit_msg>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200018": {
      "content": "<commit_after>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200019": {
      "content": "<beginning_of_sentence>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200020": {
      "content": "<end_of_sentence>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200021": {
      "content": "<end_of_document>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200022": {
      "content": "<function_call>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200023": {
      "content": "<code_interpreter>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200024": {
      "content": "<speech>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200025": {
      "content": "<image>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<beginning_of_sentence>",
  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<beginning_of_sentence>system ai_setting=assistant\\n' + message['content'][0]['text'] + '<end_of_sentence>\\n'}}{% elif message['role'] == 'user' %}{{ '<beginning_of_sentence>user name=user\\n' + message['content'][0]['text'] + '<end_of_sentence>\\n'}}{% elif message['role'] == 'assistant' %}{{ '<beginning_of_sentence>ai name=assistant\\n' }}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] }}{% endgeneration %}{% endfor %}{{ '<end_of_sentence>\\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<beginning_of_sentence>ai name=assistant\\n' }}{% endif %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<end_of_sentence>",
  "extra_special_tokens": {},
  "model_max_length": 40960000,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<end_of_document>"
}