confluence-model-test / tokenizer_config.json
dennissulejmanvisma's picture
Upload tokenizer
a780f29
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<unk>",
"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": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"chat_template": "{{ eos_token }}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content']}}{% else %}{{ 'Bot: ' + message['content']}}{% endif %}{{ message['text'] }}{{ bos_token }}{% endfor %}Bot:",
"clean_up_tokenization_spaces": true,
"do_lower_case": false,
"eos_token": "<|endoftext|>",
"keep_accents": false,
"model_max_length": 2048,
"pad_token": "<pad>",
"padding_side": "left",
"remove_space": false,
"sp_model_kwargs": {},
"tokenizer_class": "GPTSw3Tokenizer",
"truncation_side": "left",
"unk_token": "<unk>"
}