Lisennlp / distributed_train_pytorchLinks
pytorch分布式训练,支持多机多卡,单机多卡。
☆42Updated 4 years ago
Alternatives and similar repositories for distributed_train_pytorch
Users that are interested in distributed_train_pytorch are comparing it to the libraries listed below
Sorting:
- 简洁易用版TinyBert:基于Bert进行知识蒸馏的预训练语言模型☆267Updated 4 years ago
- ☆37Updated 3 years ago
- RoFormer升级版☆154Updated 3 years ago
- lightweighted deep learning inference service framework☆40Updated 4 years ago
- 论文模型复现☆43Updated 3 years ago
- 使用sentencepiece中BPE训练中文词表,并在transformers中进行使用。☆119Updated 2 years ago
- 音乐类语料的意图识别填槽以及槽值纠错模型☆17Updated 2 years ago
- The code for our ACL2022 findings paper: CRACSpell: A Contextual Typo Robust Approach with Copy Mechanism to Improve Chinese Spelling Cor…☆75Updated 3 years ago
- CTC2021-中文文本纠错大赛的SOTA方案及在线演示☆73Updated 2 years ago
- 文本智能校对大赛(Chinese Text Correction)的baseline☆68Updated 2 years ago
- A Multi-modal Model Chinese Spell Checker Released on ACL2021.☆160Updated 2 years ago
- RoFormer V1 & V2 pytorch☆512Updated 3 years ago
- Apply the Circular to the Pretraining Model☆38Updated 3 years ago
- 基于Gated Attention Unit的Transformer模型(尝鲜版)☆98Updated 2 years ago
- FLASHQuad_pytorch☆68Updated 3 years ago
- This is the official code for paper titled "Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models".☆68Updated 4 years ago
- python | 高效使用统计语言模型kenlm:新词发现、分词、智能纠错等☆168Updated 6 years ago
- 一个基于预训练的句向量生成工具☆138Updated 2 years ago
- 一个多模态内容理解算法框架,其中包含数据处理、预训练模型、常见模型以及模型加速等模块。☆320Updated 3 years ago
- 🙈 An unofficial implementation of SoftMaskedBert based on huggingface/transformers.☆97Updated 4 years ago
- 拼音转汉字, convert pinyin to 汉字 using deep networks☆23Updated 5 years ago
- ☆86Updated 4 years ago
- Chinese MobileBERT(中文MobileBERT模型)☆96Updated 3 years ago
- dpo算法实现☆44Updated last year
- code for ACL2021 paper "Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction"☆99Updated 3 years ago
- Rephrasing Language Model for CSC (AAAI 2024)☆41Updated last year
- 不用tensorflow estimator,分别采用字mask和wwm mask在中文领域内finetune bert模型☆23Updated 5 years ago
- 基于seq2edit (Gector) 的中文文本纠错。☆29Updated 2 years ago
- NTK scaled version of ALiBi position encoding in Transformer.☆69Updated 2 years ago
- ☆17Updated 2 years ago