fine_tuned_gpt2_clm-model / tokenizer_config.json
pranjal01's picture
Upload tokenizer
a35b2de
raw
history blame contribute delete
701 Bytes
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [],
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"tokenizer_file": "/home/p_r_prod/.cache/huggingface/hub/models--gpt2/snapshots/11c5a3d5811f50298f278a704980280950aedb10/tokenizer.json",
"unk_token": "<|endoftext|>"
}