| { |
| "add_bos_token": true, |
| "add_eos_token": false, |
| "add_prefix_space": false, |
| "added_tokens_decoder": { |
| "0": { |
| "content": "<PAD>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "1": { |
| "content": "<UNK>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "2": { |
| "content": "<CLS>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "3": { |
| "content": "<SEP>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "4": { |
| "content": "<MASK_TOKEN>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "5": { |
| "content": "<BOS_TOKEN>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "6": { |
| "content": "<EOS_TOKEN>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "7": { |
| "content": "<EOP_TOKEN>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "255000": { |
| "content": "<|START_OF_TURN_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255001": { |
| "content": "<|END_OF_TURN_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "255002": { |
| "content": "<|YES_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255003": { |
| "content": "<|NO_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255004": { |
| "content": "<|GOOD_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255005": { |
| "content": "<|BAD_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255006": { |
| "content": "<|USER_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255007": { |
| "content": "<|CHATBOT_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255008": { |
| "content": "<|SYSTEM_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255009": { |
| "content": "<|USER_0_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255010": { |
| "content": "<|USER_1_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255011": { |
| "content": "<|USER_2_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255012": { |
| "content": "<|USER_3_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255013": { |
| "content": "<|USER_4_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255014": { |
| "content": "<|USER_5_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255015": { |
| "content": "<|USER_6_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255016": { |
| "content": "<|USER_7_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255017": { |
| "content": "<|USER_8_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255018": { |
| "content": "<|USER_9_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255019": { |
| "content": "<|EXTRA_0_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255020": { |
| "content": "<|EXTRA_1_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255021": { |
| "content": "<|EXTRA_2_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255022": { |
| "content": "<|EXTRA_3_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255023": { |
| "content": "<|EXTRA_4_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255024": { |
| "content": "<|EXTRA_5_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255025": { |
| "content": "<|EXTRA_6_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255026": { |
| "content": "<|EXTRA_7_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255027": { |
| "content": "<|EXTRA_8_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "255028": { |
| "content": "<|EXTRA_9_TOKEN|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| } |
| }, |
| "bos_token": "<BOS_TOKEN>", |
| "chat_template": [ |
| { |
| "name": "default", |
| "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are Hormoz, a brilliant, sophisticated, multilingual AI-assistant trained to assist human users by providing thorough responses. You are able to interact and respond to questions in 23 languages and you are powered by a multilingual model built by Mann-E.' %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}" |
| }, |
| { |
| "name": "tool_use", |
| "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\nYou help people answer their questions and other requests interactively...' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Mann-E Labs...' }}{% for tool in tools %}{{'```python\ndef ' + tool.name + '('}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ ', ' }}{% endif %}{{ param_name }}: {{ param_fields.type if param_fields.required else 'Optional[' + param_fields.type + '] = None' }}{% endfor %}{{ ') -> List[Dict]:\n + tool.description + \n pass\n```' }}{% endfor %}" |
| }, |
| { |
| "name": "rag", |
| "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\nYou help people answer their questions and other requests interactively...' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere...' }}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '<results>' }}{% for document in documents %}{{ '\nDocument: ' }}{{ loop.index0 }}\n{% for key, value in document.items() %}{{ key }}: {{ value }}\n{% endfor %}{% endfor %}{{ '</results>' }}{{ '<|END_OF_TURN_TOKEN|>' }}" |
| } |
| ], |
| "clean_up_tokenization_spaces": false, |
| "eos_token": "<|END_OF_TURN_TOKEN|>", |
| "extra_special_tokens": {}, |
| "legacy": true, |
| "merges_file": null, |
| "model_max_length": 1000000000000000019884624838656, |
| "pad_token": "<PAD>", |
| "sp_model_kwargs": {}, |
| "spaces_between_special_tokens": false, |
| "tokenizer_class": "CohereTokenizer", |
| "unk_token": null, |
| "use_default_system_prompt": false, |
| "vocab_file": null |
| } |
|
|