xglm_instruct_for_pretraining / tokenizer_config.json
Den4ikAI's picture
Upload with huggingface_hub
e2f6ed9
raw
history blame contribute delete
654 Bytes
{
"additional_special_tokens": [
"<madeupword0>",
"<madeupword1>",
"<madeupword2>",
"<madeupword3>",
"<madeupword4>",
"<madeupword5>",
"<madeupword6>"
],
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"name_or_path": "facebook/xglm-2.9B",
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": "/home/ubuntu/.cache/huggingface/hub/models--facebook--xglm-2.9B/snapshots/33c659ae27de09c0a54123d3902dac48cbb8592a/special_tokens_map.json",
"tokenizer_class": "XGLMTokenizer",
"unk_token": "<unk>"
}