smallama-it / tokenizer_config.json
nroggendorff's picture
Training loss: 6.7703
37b3756 verified
raw
history blame
2.45 kB
{
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"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
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1108": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1109": {
"content": "<|bot|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1110": {
"content": "<|end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|user|>",
"<|bot|>",
"<|end|>"
],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '<|end|>\n' }}{% elif message['role'] == 'assistant' %}{{ '<|bot|>\n' + message['content'] + '<|end|>\n' + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"mask_token": "<mask>",
"max_length": 512,
"model_max_length": 1000000000000000019884624838656,
"pad_to_multiple_of": null,
"pad_token": "<pad>",
"pad_token_type_id": 0,
"padding_side": "right",
"stride": 0,
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>"
}