148 lines
3.6 KiB
JSON
148 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": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"2": {
|
|
"content": "</s>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"61366": {
|
|
"content": "<pad>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"61367": {
|
|
"content": "<|system|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": true,
|
|
"special": true
|
|
},
|
|
"61368": {
|
|
"content": "<|user|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": true,
|
|
"special": true
|
|
},
|
|
"61369": {
|
|
"content": "<|assistant|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": true,
|
|
"special": true
|
|
},
|
|
"61370": {
|
|
"content": "<|context|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": true,
|
|
"special": true
|
|
},
|
|
"61371": {
|
|
"content": "<|/context|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": true,
|
|
"special": true
|
|
},
|
|
"61372": {
|
|
"content": "[INST]",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": true,
|
|
"special": true
|
|
},
|
|
"61373": {
|
|
"content": "[/INST]",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": true,
|
|
"special": true
|
|
},
|
|
"61374": {
|
|
"content": "<|translate-en-el|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": true,
|
|
"special": true
|
|
},
|
|
"61375": {
|
|
"content": "<|translate-el-en|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": true,
|
|
"special": true
|
|
},
|
|
"61376": {
|
|
"content": "<|tldr|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": true,
|
|
"special": true
|
|
}
|
|
},
|
|
"additional_special_tokens": [
|
|
"<|system|>",
|
|
"<|user|>",
|
|
"<|assistant|>",
|
|
"<|context|>",
|
|
"<|/context|>",
|
|
"[INST]",
|
|
"[/INST]",
|
|
"<|translate-en-el|>",
|
|
"<|translate-el-en|>",
|
|
"<|tldr|>"
|
|
],
|
|
"bos_token": "<s>",
|
|
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\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,
|
|
"cls_token": "<s>",
|
|
"eos_token": "</s>",
|
|
"legacy": true,
|
|
"mask_token": "<unk>",
|
|
"model_max_length": 1000000000000000019884624838656,
|
|
"pad_token": "<pad>",
|
|
"sep_token": "</s>",
|
|
"sp_model_kwargs": {},
|
|
"spaces_between_special_tokens": false,
|
|
"tokenizer_class": "LlamaTokenizer",
|
|
"unk_token": "<unk>",
|
|
"use_default_system_prompt": false,
|
|
"use_fast": true
|
|
}
|