darija-english-assistant / tokenizer_config.json
Anassk's picture
Training in progress, step 20
9c31d91 verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": null,
"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
}
},
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{{ 'Below are some instructions that describe some tasks. Write responses that appropriately complete each request.' }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '\n\n ### Instruction:\n ' + message['content'] }}{% elif message['role'] == 'assistant' %}{{ '\n\n ### Response:\n ' + message['content'] + '</s>' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n\n ### Response:\n ' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 4096,
"pad_token": "<unk>",
"padding_side": "left",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}