GPT2-Guanaco-LoRA / tokenizer_config.json
harigovind511's picture
GPT2 finetuned on Guanaco dataset, 3 epochs.
b1ea2fb
raw
history blame
234 Bytes
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1024,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}