tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "100256": {
      "content": "<|_unuse_missing_100256|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100257": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100258": {
      "content": "<|fim_prefix|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100259": {
      "content": "<|fim_middle|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100260": {
      "content": "<|fim_suffix|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100261": {
      "content": "<|_unuse_missing_100261|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100262": {
      "content": "<|_unuse_missing_100262|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100263": {
      "content": "<|_unuse_missing_100263|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100264": {
      "content": "<|_unuse_missing_100264|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100265": {
      "content": "<|_unuse_missing_100265|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100266": {
      "content": "<|_unuse_missing_100266|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100267": {
      "content": "<|_unuse_missing_100267|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100268": {
      "content": "<|_unuse_missing_100268|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100269": {
      "content": "<|_unuse_missing_100269|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100270": {
      "content": "<|_unuse_missing_100270|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100271": {
      "content": "<|_unuse_missing_100271|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100272": {
      "content": "<|_unuse_missing_100272|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100273": {
      "content": "<|_unuse_missing_100273|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100274": {
      "content": "<|_unuse_missing_100274|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100275": {
      "content": "<|_unuse_missing_100275|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100276": {
      "content": "<|endofprompt|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|endoftext|>",
    "<|fim_prefix|>",
    "<|fim_middle|>",
    "<|fim_suffix|>",
    "<|endofprompt|>",
    "<|_unuse_missing_100256|>",
    "<|_unuse_missing_100261|>",
    "<|_unuse_missing_100262|>",
    "<|_unuse_missing_100263|>",
    "<|_unuse_missing_100264|>",
    "<|_unuse_missing_100265|>",
    "<|_unuse_missing_100266|>",
    "<|_unuse_missing_100267|>",
    "<|_unuse_missing_100268|>",
    "<|_unuse_missing_100269|>",
    "<|_unuse_missing_100270|>",
    "<|_unuse_missing_100271|>",
    "<|_unuse_missing_100272|>",
    "<|_unuse_missing_100273|>",
    "<|_unuse_missing_100274|>",
    "<|_unuse_missing_100275|>"
  ],
  "bos_token": "<|endoftext|>",
  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set merged_content = messages[0]['content'] + ' ' + messages[1]['content'] %}{% set merged_messages = [{'role': messages[1]['role'], 'content': merged_content}] + messages[2:] %}{% else %}{% set merged_messages = messages %}{% endif %}{% for message in merged_messages %}{{message['role'] + ': ' + (message['content'].split('<reasoning>')[0] + message['content'].split('</reasoning>')[1] if message['role'] == 'assistant' and '</reasoning>' in message['content'] else message['content'])}}{% if (loop.last and add_generation_prompt and merged_messages[-1]['role'] != 'assistant') or not loop.last %}{{ ' <sep> ' }}{% endif %}{% endfor %}{% if add_generation_prompt and merged_messages[-1]['role'] != 'assistant' %}{{ 'assistant:' }}{% endif %}",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "model_max_length": 32768,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}