legml-v0.1 / tokenizer_config.json
malhajar's picture
Update tokenizer_config.json
ba757a2 verified
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"chat_template": "{%- if tools %} {{- '<|im_start|>system\\n' }} {%- if messages[0]['role'] == 'system' %} {{- messages[0]['content'] }} {%- else %} {{- 'Vous êtes un assistant utile.' }} {%- endif %} {{- \"\\n\\n# Outils\\n\\nVous pouvez appeler une ou plusieurs fonctions pour aider avec la requête de l'utilisateur.\\n\\nVous disposez des signatures de fonctions dans les balises XML <tools></tools>:\\n<tools>\" }} {%- for tool in tools %} {{- \"\\n\" }} {{- tool | tojson }} {%- endfor %} {{- \"\\n</tools>\\n\\nPour chaque appel de fonction, renvoyez un objet JSON avec le nom de la fonction et les arguments dans les balises XML <tool_call></tool_call>.\\n<|im_end|>\\n\" }}{%- else %} {%- if messages[0]['role'] == 'system' %} {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }} {%- else %} {{- '<|im_start|>system\\nVous êtes un assistant utile.<|im_end|>\\n' }} {%- endif %}{%- endif %}{%- for message in messages %} {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %} {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }} {%- elif message.role == \"assistant\" %} {{- '<|im_start|>' + message.role }} {%- if message.content %} {{- '\\n' + message.content }} {%- endif %} {%- for tool_call in message.tool_calls %} {%- if tool_call.function is defined %} {%- set tool_call = tool_call.function %} {%- endif %} {{- '\\n<tool_call>{\"name\": \"' + tool_call.name + '\", \"arguments\": ' + (tool_call.arguments | tojson) + '}</tool_call>' }} {%- endfor %} {{- '<|im_end|>\\n' }} {%- elif message.role == \"tool\" %} {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %} {{- '<|im_start|>user' }} {%- endif %} {{- '\\n<tool_response>\\n' }} {{- message.content }} {{- '\\n</tool_response>' }} {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %} {{- '<|im_end|>\\n' }} {%- endif %} {%- endif %}{%- endfor %}{%- if add_generation_prompt %} {{- '<|im_start|>assistant\\n' }}{%- endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}