gpt2_pycode / tokenizer_config.json
maharnab's picture
Upload 4 files
30e718e verified
raw
history blame
1.82 kB
{
"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": "<sos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50259": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50260": {
"content": "<user>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50261": {
"content": "</user>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50262": {
"content": "<assistant>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50263": {
"content": "</assistant>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<user>",
"</user>",
"<assistant>",
"</assistant>"
],
"bos_token": "<sos>",
"clean_up_tokenization_spaces": true,
"eos_token": "<eos>",
"errors": "replace",
"model_max_length": 1024,
"pad_token": "<pad>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}