tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<repo_name>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<reponame>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "<file_sep>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<filename>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "<gh_stars>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "8": {
      "content": "<issue_start>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "9": {
      "content": "<issue_comment>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "10": {
      "content": "<issue_closed>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "11": {
      "content": "<jupyter_start>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "12": {
      "content": "<jupyter_text>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13": {
      "content": "<jupyter_code>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "14": {
      "content": "<jupyter_output>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "15": {
      "content": "<jupyter_script>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "16": {
      "content": "<empty_output>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49152": {
      "content": "<fake_token_around_image>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49153": {
      "content": "<image>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49154": {
      "content": "<end_of_utterance>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<fake_token_around_image>",
    "<image>",
    "<end_of_utterance>"
  ],
  "bos_token": "<|im_start|>",
  "chat_template": "{%- set config = namespace(has_system_message=false, has_tools=false) -%}{%- set system_messages = messages | selectattr('role', 'equalto', 'system') | list -%}{%- set config.has_system_message = system_messages | length > 0 -%}{%- set config.has_tools = tools is not none and tools | length > 0 -%}{%- if not config.has_system_message -%}{%- set messages = [{ \"content\": \"You are an AI agent acting as a human assistant.\", \"role\": \"system\" }] + messages -%}{%- endif -%}{%- for message in messages -%}{% if loop.first %}{{ bos_token }}{% endif %}{{ message.role | capitalize }}:{{ ' ' }}{%- if message.role == 'system' -%}{{ message.content }}{%- if config.has_tools -%}{{ '\n\n' }}You are aware of the following tools in your environment:\n{\n  \"tools\": [\n  {% for tool in tools %}\n    {\n      \"function\": {\n        \"description\": \"{{ tool.function.description }}\",\n        \"name\": \"{{ tool.function.name }}\",\n        \"parameters\": {{ tool.function.parameters | tojson }}\n      },\n      \"type\": \"{{ tool.type }}\"\n    }{% if not loop.last %},{% endif %}\n\n  {% endfor %}\n  ]\n}\n\nIf you would like to suggest one or more tool calls, please respond in the following format:\n{\n  \"finish_reason\": \"tool_calls\",\n  \"tool_calls\": [\n    {\n      \"arguments\": \"{\\\"parameter_name\\\": \\\"parameter_value\\\"}\",\n      \"id\": \"call_id\",\n      \"name\": \"tool_name\"\n    }\n  ]\n}\n{%- endif -%}<end_of_utterance>{{ '\n' }}{%- endif -%}{%- if message.role == 'user' -%}{% if message['content'] is string %}{{message['content']}}{% else %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] in ['image', 'image_url'] %}{{ '<image>' }}{% endif %}{% endfor %}{% endif %}<end_of_utterance>{{ '\n' }}{%- endif -%}{%- if message.role == 'assistant' -%}{% generation %}{%- if message.tool_calls | default(false) -%}\n{\n  \"finish_reason\": \"tool_calls\",\n  \"tool_calls\": [\n  {% for tool_call in message.tool_calls %}\n    {\n      \"arguments\": {{ tool_call.function.arguments | tojson }},\n      \"id\": \"{{ tool_call.id }}\",\n      \"name\": \"{{ tool_call.function.name }}\"\n    }{% if not loop.last %},{% endif %}\n\n  {% endfor %}\n  ]\n}\n{%- else -%}{{ message.content }}{%- endif -%}{% endgeneration %}<end_of_utterance>{{ '\n' }}{%- endif -%}{%- if message.role == 'tool' -%}\n{\n  \"content\": {{ message.content | tojson }},\n  \"name\": \"{{ message.name }}\",\n  \"tool_call_id\": \"{{ message.tool_call_id }}\"\n}\n<end_of_utterance>{{ '\n' }}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}Assistant:{{ ' ' }}{%- endif -%}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<end_of_utterance>",
  "legacy": false,
  "model_max_length": 16384,
  "pad_token": "<|im_end|>",
  "padding_side": "left",
  "processor_class": "Idefics3Processor",
  "tokenizer_class": "GPT2Tokenizer",
  "truncation_side": "left",
  "unk_token": "<|endoftext|>",
  "vocab_size": 49152
}