phi-pl-400M-v_0_1 / tokenizer_config.json
teddy-f-47's picture
Training in progress, step 1000
0dca5dd
raw
history blame
476 Bytes
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 2048,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CodeGenTokenizer",
"unk_token": "<|endoftext|>"
}