lonePatient / Nezha_chinese_pytorch
Licence: mit
NEZHA: Neural Contextualized Representation for Chinese Language Understanding
Stars: ✭ 65
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Nezha chinese pytorch
LM-CNLC
Chinese Natural Language Correction via Language Model
Stars: ✭ 15 (-76.92%)
Mutual labels: chinese, language-model
Clue
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
Stars: ✭ 2,425 (+3630.77%)
Mutual labels: chinese, language-model
Char Rnn Chinese
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch. Based on code of https://github.com/karpathy/char-rnn. Support Chinese and other things.
Stars: ✭ 192 (+195.38%)
Mutual labels: chinese, language-model
Chinese-Word-Segmentation-in-NLP
State of the art Chinese Word Segmentation with Bi-LSTMs
Stars: ✭ 23 (-64.62%)
Mutual labels: chinese, language-model
Nlp chinese corpus
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
Stars: ✭ 6,656 (+10140%)
Mutual labels: chinese, language-model
Chinese Electra
Pre-trained Chinese ELECTRA(中文ELECTRA预训练模型)
Stars: ✭ 830 (+1176.92%)
Mutual labels: chinese, language-model
Lightnlp
基于Pytorch和torchtext的自然语言处理深度学习框架。
Stars: ✭ 739 (+1036.92%)
Mutual labels: chinese, language-model
Char rnn lm zh
language model in Chinese,基于Pytorch官方文档实现
Stars: ✭ 57 (-12.31%)
Mutual labels: chinese, language-model
Pime
Develop input methods for Windows easily with Python and node.js
Stars: ✭ 1,051 (+1516.92%)
Mutual labels: chinese
Lmchallenge
A library & tools to evaluate predictive language models.
Stars: ✭ 47 (-27.69%)
Mutual labels: language-model
Cross Domain ner
Cross-domain NER using cross-domain language modeling, code for ACL 2019 paper
Stars: ✭ 67 (+3.08%)
Mutual labels: language-model
Indonesian Language Models
Indonesian Language Models and its Usage
Stars: ✭ 64 (-1.54%)
Mutual labels: language-model
Emacs Document
translate emacs documents to Chinese for convenient reference
Stars: ✭ 1,085 (+1569.23%)
Mutual labels: chinese
NeZha_Chinese_PyTorch
pytorch版NEZHA,适配transformers
论文下载地址: NEZHA: Neural Contextualized Representation for Chinese Language Understanding
运行脚本依赖模块
如果需要运行该案例脚本,需要安装以下模块:
模型权重下载
官方提供的Tensorflow版本权重下载地址:huawei-noah
已经转化为PyTorch版本权重下载地址如下:
-
nezha-cn-base 百度网盘链接 提取码: hckq
-
nezha-large-zh 百度网盘链接 提取码: qks2
-
nezha-base-wwm 百度网盘链接 提取码: ysg3
-
nezha-large-wwm 百度网盘链接 提取码: 8dig
说明:若加载的模型权重是从下列百度网盘下载的PyTorch模型权重,则需要保证torch版本>=1.6.0
运行
执行命令:
sh scripts/run_task_text_classification_chnsenti.sh
长文本
长文本可以通过设置config.max_position_embeddings
参数实现,默认值为512,如:
config.max_position_embeddings=args.train_max_seq_length
结果
NEZHA(base-wwm) | chnsenti |
---|---|
tensorflow | 94.75 |
pytorch | 94.92 |
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].