tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "100256": {
      "content": "<|extra_id_0|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "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": "|||PHONE_NUMBER|||",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100262": {
      "content": "|||EMAIL_ADDRESS|||",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100263": {
      "content": "|||IP_ADDRESS|||",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100264": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100265": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100266": {
      "content": "<|extra_id_1|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100267": {
      "content": "<|extra_id_2|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100268": {
      "content": "<|extra_id_3|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100269": {
      "content": "<|extra_id_4|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100270": {
      "content": "<|extra_id_5|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100271": {
      "content": "<|extra_id_6|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100272": {
      "content": "<|extra_id_7|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100273": {
      "content": "<|extra_id_8|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100274": {
      "content": "<|extra_id_9|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100275": {
      "content": "<|extra_id_10|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100276": {
      "content": "<|endofprompt|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100277": {
      "content": "<|pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|endoftext|>",
  "chat_template": "{% set has_system = messages|selectattr('role', 'equalto', 'system')|list|length > 0 %}{% if not has_system %}{{ '<|im_start|>system\nYou are Olmo, a helpful AI assistant built by Ai2. Your date cutoff is December 2024, and your model weights are available at https://huggingface.co/allenai.<|im_end|>\n' }}{% endif %}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|im_start|>system\n' + message['content'] }}{% if message.get('functions', none) is not none %}{{ ' <functions>' + message['functions'] + '</functions><|im_end|>\n' }}{% else %}{{ ' You do not currently have access to any functions. <functions></functions><|im_end|>\n' }}{% endif %}{% elif message['role'] == 'user' %}{% if message.get('functions', none) is not none %}{{ '<|im_start|>user\n' + message['content'] + '\n' + '<functions>' + message['functions'] + '</functions><|im_end|>\n' }}{% else %}{{ '<|im_start|>user\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '<|im_start|>assistant\n' }}{% if message.get('content', none) is not none %}{{ message['content'] }}{% endif %}{% if message.get('function_calls', none) is not none %}{{ '<function_calls>' + message['function_calls'] + '</function_calls>' }}{% endif %}{% if not loop.last %}{{ '<|im_end|>' + '\n' }}{% else %}{{ eos_token }}{% endif %}{% elif message['role'] == 'environment' %}{{ '<|im_start|>environment\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|im_start|>assistant\n<think>' }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "model_max_length": 65536,
  "pad_token": "<|pad|>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}