taishan1994 / PPO_Chinese_GenerateLinks
☆11Updated 2 years ago
Alternatives and similar repositories for PPO_Chinese_Generate
Users that are interested in PPO_Chinese_Generate are comparing it to the libraries listed below
Sorting:
- BLOOM 模型的指令微调☆24Updated 2 years ago
- using lear to do ner extraction☆29Updated 3 years ago
- ☆57Updated 3 years ago
- pytorch Efficient GlobalPointer☆56Updated 3 years ago
- pytorch版unilm模型☆27Updated 4 years ago
- 基于Bart语言模型的指针生成网络,用于中文语法纠错任务☆16Updated 3 years ago
- 记录NLP、CV、搜索、推荐等AI岗位最新情况。☆28Updated 2 years ago
- 句子匹配模型,包括无监督的SimCSE、ESimCSE、PromptBERT,和有监督的SBERT、CoSENT。☆99Updated 3 years ago
- Knowledge Graph☆176Updated 3 years ago
- 基于模板的文本纠错;Automatically Mining Error Templates for Grammatical Error Correction☆44Updated 3 years ago
- 基于pytorch的百度UIE命名实体识别。☆57Updated 2 years ago
- CCKS2021答非所问竞赛冠军方案☆27Updated 4 years ago
- 基于PaddleNLP开源的抽取式UIE进行医学命名实体识别(torch实现)☆44Updated 3 years ago
- GoGPT:基于Llama/Llama 2训练的中英文增强大模型|Chinese-Llama2☆79Updated 2 years ago
- GlobalPointer的优化版/NER实体识别☆122Updated 3 years ago
- 基于 pytorch 的 bert 实现和下游任务微调☆53Updated 3 years ago
- CoSENT、STS、SentenceBERT☆171Updated 11 months ago
- a baseline to practice☆45Updated 4 years ago
- 百度2021年语言与智能技术竞赛多形态信息抽取赛道事件抽取部分torch版baseline☆80Updated 4 years ago
- 实验苏神的CoSENT的Torch实现☆33Updated 4 years ago
- ☆32Updated 4 years ago
- 这里是用torch写的简洁版的GLUE评测代码。This is the simpler code written by torch in GLUE.☆19Updated 3 years ago
- 中文数据集下SimCSE+ESimCSE的实现☆193Updated 3 years ago
- [TALLIP] General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretraining☆63Updated last year
- 格物-多语言和中文大规模预训练模型-轻量版,涵盖纯中文、知识增强、113个语种多语言,采用主流Roberta架构,适用于NLU和NLG任务, 支持pytorch、tensorflow、uer、huggingface等框架。 Multilingual and Chinese …☆30Updated 3 years ago
- ☆41Updated 4 years ago
- Grammar correct project based Tencent's paper(Sequence to Action)☆15Updated 3 years ago
- 文本智能校对大赛(Chinese Text Correction)的baseline☆67Updated 3 years ago
- 收集了目前为止中文领域的MRC抽取式数据集☆122Updated last year
- NLP实验:新词挖掘+预训练模型继续Pre-training☆47Updated 2 years ago