227 lines
5.6 KiB
JSON
227 lines
5.6 KiB
JSON
|
|
{
|
||
|
|
"add_bos_token": false,
|
||
|
|
"add_eos_token": false,
|
||
|
|
"add_prefix_space": false,
|
||
|
|
"added_tokens_decoder": {
|
||
|
|
"0": {
|
||
|
|
"content": "<|endoftext|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"1": {
|
||
|
|
"content": "<|padding|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"50254": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50255": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50256": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50257": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50258": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50259": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50260": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50261": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50262": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50263": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50264": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50265": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50266": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50267": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50268": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50269": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50270": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50271": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50272": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50273": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50274": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50275": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50276": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50277": {
|
||
|
|
"content": "<end_of_turn>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"bos_token": "<|endoftext|>",
|
||
|
|
"chat_template": "{{ '<|endoftext|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 and system_message is defined %}{% set content = system_message + '\n\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '<start_of_turn>user\n' + content + '<end_of_turn>\n<start_of_turn>model\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<end_of_turn>\n' }}{% endif %}{% endfor %}",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": "<end_of_turn>",
|
||
|
|
"extra_special_tokens": {},
|
||
|
|
"model_max_length": 1000000000000000019884624838656,
|
||
|
|
"pad_token": "<end_of_turn>",
|
||
|
|
"padding_side": "right",
|
||
|
|
"split_special_tokens": false,
|
||
|
|
"tokenizer_class": "GPTNeoXTokenizer",
|
||
|
|
"unk_token": "<|endoftext|>"
|
||
|
|
}
|