opt-350m-lora-yoda / tokenizer_config.json
dvgodoy's picture
Upload tokenizer
4af07f5 verified
{
"add_bos_token": true,
"add_prefix_space": false,
"added_tokens_decoder": {
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50265": {
"content": "<|pad|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50266": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50267": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": "<|im_start|>",
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|im_end|>",
"errors": "replace",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|pad|>",
"padding_side": "left",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "</s>"
}