Llama-Baseline-V4-Instruct-Test / tokenizer_config.json
nosuchjihyun's picture
(Trained with Unsloth)
7b32e4e verified
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<classification>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<bos>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
"clean_up_tokenization_spaces": false,
"cls_token": "<classification>",
"eos_token": "<eos>",
"extra_special_tokens": {},
"mask_token": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 8192,
"pad_token": "<pad>",
"padding_side": "left",
"sep_token": null,
"split_special_tokens": false,
"tokenizer_class": "GPT2Tokenizer",
"truncation_side": "right",
"unk_token": "<unk>"
}