PyLoomer_CodeParrot / tokenizer_config.json
anujsahani01's picture
Training in progress, step 500
7c40aca
raw
history blame
1.48 kB
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32768": {
"content": "<|PAD|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32769": {
"content": "<SYSTEM_TASK:>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32770": {
"content": "<USER_TASK:>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32771": {
"content": "<ASSISTANT_TASK:>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32772": {
"content": "<END_TASK>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<SYSTEM_TASK:>",
"<USER_TASK:>",
"<ASSISTANT_TASK:>",
"<END_TASK>"
],
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 5000,
"pad_token": "<|PAD|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}