YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

NeZha-Pytorch

pytorch版NEZHA,适配transformers

安装

pip install git+https://github.com/yanqiangmiffy/Nezha-Pytorch.git

权重下载地址

https://github.com/lonePatient/NeZha_Chinese_PyTorch

torch使用样例

import torch
from transformers import BertTokenizer
from nezha import NeZhaModel, NeZhaConfig

text = "今天[MASK]很好,我[MASK]去公园玩。"
tokenizer = BertTokenizer.from_pretrained(
    "quincyqiang/nezha-cn-base"
)
model = NeZhaModel.from_pretrained(
    "quincyqiang/nezha-cn-base"
)

config = NeZhaConfig.from_pretrained(
    "quincyqiang/nezha-cn-base"
)
model.eval()
inputs = tokenizer(text, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)
Downloads last month
11
Inference API
Unable to determine this model’s pipeline type. Check the docs .