File size: 6,754 Bytes
db18629 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 |
{
"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
}
|