persian-llama2 / tokenizer_config.json
amirakhlaghiqqq's picture
[Added] - Special Tokens to indicate Farsi and English text has been added
d6e48cb
raw
history blame
3.28 kB
{
"add_bos_token": true,
"add_eos_token": false,
"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
},
"36943": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"36944": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"36945": {
"content": "<|EN|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"36946": {
"content": "<|FA|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"36947": {
"content": "<|placeholder3|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"36948": {
"content": "<|placeholder4|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"36949": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"36950": {
"content": "<|end|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"36951": {
"content": "<|placeholder5|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"36952": {
"content": "<|placeholder6|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"36953": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": false,
"model_max_length": 4096,
"pad_token": "<|endoftext|>",
"padding_side": "left",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}