rs-tinyllama-alpaca_gpt4-20K / tokenizer_config.json
Jason Lee
End of training
fedc122 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": "{% if messages[0]['role'] == 'system' %}{% set offset = 1 %}{% else %}{% set offset = 0 %}{% endif %}{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == offset) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>' + 'assistant' + '<|end_header_id|>\n\n' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}