IDEA-CCNL
/

Randeng-T5-77M-MultiTask-Chinese

Text2Text Generation Transformers PyTorch Safetensors Chinese t5 Text2Text Generation T5 chinese sentencepiece Inference Endpoints text-generation-inference

Model card Files Files and versions Community

Randeng-T5-77M-MultiTask-Chinese / tokenizer_config.json

wuxiaojun

init commit

0f9529a over 1 year ago

raw history blame contribute delete

No virus

439 Bytes

{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": [], "sp_model_kwargs": {}, "name_or_path": "/cognitive_comp/wuxiaojun/pretrained/pytorch/Randeng-T5-77M", "special_tokens_map_file": "/cognitive_comp/ganruyi/experiments/t5_cn_small_pretrain/Randeng-T5-77M/special_tokens_map.json", "do_lower_case": true, "max_length": 1024, "truncation": true, "tokenizer_class": "T5Tokenizer"}