149 lines
3.6 KiB
JSON
149 lines
3.6 KiB
JSON
{
|
|
"add_bos_token": true,
|
|
"add_eos_token": false,
|
|
"add_prefix_space": true,
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "<unk>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"1": {
|
|
"content": "<s>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"2": {
|
|
"content": "</s>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"79085": {
|
|
"content": "<|future_token_0|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"79086": {
|
|
"content": "<|future_token_1|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"79087": {
|
|
"content": "<|future_token_2|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"79088": {
|
|
"content": "<|future_token_3|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"79089": {
|
|
"content": "<|future_token_4|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"79090": {
|
|
"content": "<|future_token_5|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"79091": {
|
|
"content": "<|future_token_6|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"79092": {
|
|
"content": "<|future_token_7|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"79093": {
|
|
"content": "<|future_token_8|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"79094": {
|
|
"content": "<|future_token_9|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"79095": {
|
|
"content": "<|future_token_10|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"79096": {
|
|
"content": "<|future_token_11|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"79097": {
|
|
"content": "<|im_end|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"bos_token": "<s>",
|
|
"chat_template": "<s>{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|im_end|>",
|
|
"legacy": true,
|
|
"model_max_length": 32768,
|
|
"pad_token": "<|im_end|>",
|
|
"padding_side": "right",
|
|
"sp_model_kwargs": {},
|
|
"spaces_between_special_tokens": false,
|
|
"tokenizer_class": "LlamaTokenizer",
|
|
"unk_token": "<unk>",
|
|
"use_default_system_prompt": true
|
|
}
|