TinyLlama-SFT-Unsloth-QLoRA / tokenizer_config.json
RonanMcGovern's picture
Upload tokenizer
a4f425a verified
raw
history blame
1.41 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": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"mask_token": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 2048,
"pad_token": "<unk>",
"padding_side": "left",
"sep_token": null,
"split_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"unk_token": "<unk>",
"use_default_system_prompt": false
}