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
    },
    "100278": {
      "content": "<im_start>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100279": {
      "content": "<im_end>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100280": {
      "content": "<im_patch>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100281": {
      "content": "<im_col>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100282": {
      "content": "<|image|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<im_start>",
    "<im_end>",
    "<im_patch>",
    "<im_col>",
    "<|image|>"
  ],
  "auto_map": {
    "AutoProcessor": "preprocessing_molmo.MolmoProcessor"
  },
  "bos_token": "<|endoftext|>",
  "chat_template": "{% for message in messages -%}\n        {%- if (loop.index % 2 == 1 and message['role'] != 'user') or \n          (loop.index % 2 == 0 and message['role'].lower() != 'assistant') -%}\n        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}\n        {%- endif -%}\n        {{ message['role'].capitalize() + ': ' + message['content'] }}\n        {%- if not loop.last -%}\n        {{ ' ' }}\n        {%- endif %}\n        {%- endfor -%}\n        {%- if add_generation_prompt -%}\n        {{ ' Assistant:' }}\n        {%- endif %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "model_max_length": 8192,
  "pad_token": "<|pad|>",
  "processor_class": "MolmoProcessor",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}