43 lines
1.4 KiB
JSON
43 lines
1.4 KiB
JSON
|
{
|
||
|
|
"added_tokens_decoder": {
|
||
|
|
"0": {
|
||
|
|
"content": "<unk>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"1": {
|
||
|
|
"content": "<|startoftext|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"2": {
|
||
|
|
"content": "<|endoftext|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"bos_token": "<|startoftext|>",
|
||
|
|
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|Human|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|System|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|Assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|Assistant|>' }}\n{% endif %}\n{% endfor %}",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": "<|endoftext|>",
|
||
|
|
"legacy": false,
|
||
|
|
"model_max_length": 2048,
|
||
|
|
"pad_token": "<unk>",
|
||
|
|
"padding_side": "right",
|
||
|
|
"sp_model_kwargs": {},
|
||
|
|
"spaces_between_special_tokens": false,
|
||
|
|
"tokenizer_class": "LlamaTokenizer",
|
||
|
|
"truncation_side": "left",
|
||
|
|
"unk_token": "<unk>",
|
||
|
|
"use_default_system_prompt": false
|
||
|
|
}
|