tokenizer_config.json

{
  "add_bos_token": false,
  "add_eos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "199999": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200018": {
      "content": "<|endofprompt|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200019": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200020": {
      "content": "<|end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200021": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200022": {
      "content": "<|system|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200023": {
      "content": "<|tool|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200024": {
      "content": "<|/tool|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200025": {
      "content": "<|tool_call|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200026": {
      "content": "<|/tool_call|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200027": {
      "content": "<|tool_response|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200028": {
      "content": "<|tag|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|endoftext|>",
  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<|endoftext|>' + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|endoftext|>' + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "extra_special_tokens": {},
  "model_max_length": 131072,
  "pad_token": "<|endoftext|>",
  "padding_side": "left",
  "split_special_tokens": false,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}