longformer_cosmos / tokenizer_config.json
Shaier's picture
Training in progress, epoch 0
1d48a54
{
"add_prefix_space": false,
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"model_max_length": 4096,
"name_or_path": "allenai/longformer-base-4096",
"pad_token": "<pad>",
"padding": true,
"sep_token": "</s>",
"special_tokens_map_file": null,
"tokenizer_class": "LongformerTokenizer",
"trim_offsets": true,
"truncation": true,
"unk_token": "<unk>"
}