letstalk / tokenizer_config.json
minkhantycc's picture
Upload tokenizer_config.json with huggingface_hub
3eb843c verified
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50257": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50258": {
"content": "<startofstring>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50259": {
"content": "<endofstring>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50260": {
"content": "<bot>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<startofstring>",
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ bos_token + message['content'].strip()+'\n' }}{% elif message['role'] == 'assistant' %}{{ '<bot>' + message['content'] + eos_token+'\n' }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<endofstring>",
"errors": "replace",
"model_max_length": 1024,
"pad_token": "<pad>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}