phi_llm_v5 / tokenizer_config.json
tony
update
bcf3608
{
"add_bos_token": false,
"add_eos_token": false,
"add_prefix_space": null,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"32000": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32002": {
"content": "<|placeholder1|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32003": {
"content": "<|placeholder2|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32004": {
"content": "<|placeholder3|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32005": {
"content": "<|placeholder4|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32006": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32007": {
"content": "<|end|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32008": {
"content": "<|placeholder5|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32009": {
"content": "<|placeholder6|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32010": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + 'You are an advanced AI model capable of writing Python code. Your task is to write a single Python function with multiple Python libraries to solve the problem based on the provided intent and description.\n- Please follow the format requirements.\n- Please include requirements and terminal-based input-output examples in the function docstring.\n- The function should contain complex logic like if-else statements and loops.\n- You have to use more than three Python libraries for a scenario.\n- Try to avoid using web APIs if possible.\n- If there are any constants (e.g. strings and numeric values) used in the functions, you need to declare them before the function.\n- If data is used, you need to provide sample data in the comment.\n- Try to return values for correctness assertion.\n\nIf I provide the following intent:\n\n--start of the intent---\nwrite a function <signature> to:\n<description>\n\nThe function should output with:\n<returns>\n\nYou should start with:\n<import_libraries>\n<signature>\n\n---end of the intent---\n\nThen you need to implement the function and strictly output in below format:\n\n--start of the sample output--\npython\n<import_libraries>\n\n<global variables declaration if needed>\n\n<signature>:\n \"\"\"\n <description>\n\n Parameters:\n - <parameters>\n\n Requirements:\n - <libraries from the import_libraries part, no matter if they are used or not>\n\n Example:\n >>> <example_input>\n >>> result = <signature>(<example_input>)\n >>> print(result)\n <example_output>\n\n Returns:\n <returns>\n \"\"\"\n\n <Your implementation of the function>\n\n--end of the sample output--' + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": false,
"model_max_length": 131072,
"pad_token": "<|placeholder6|>",
"padding_side": "left",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}