zejunwang1 / gpt2ppl-zh
基于中文 GPT2 预训练模型的语句困惑度计算
☆15Updated 2 years ago
Alternatives and similar repositories for gpt2ppl-zh
Users that are interested in gpt2ppl-zh are comparing it to the libraries listed below
Sorting:
- This repository implements a prompt tuning model for hierarchical text classification. This work has been accepted as the long paper "HPT…☆66Updated last year
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆61Updated 11 months ago
- 继续预训练中文bert☆30Updated 3 years ago
- This repository stores the code of the data augmentation method from Chinese word and character levels, which adds noise to words and cha…☆18Updated 2 years ago
- ☆29Updated last year
- Summary and comparison of Chinese classification models☆34Updated 2 years ago
- ☆10Updated 2 years ago
- 2021 搜狐校园文本匹配算法大赛方案☆17Updated 6 months 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☆15Updated 2 years ago
- SimCSE中文语义相似度对比学习模型☆85Updated 3 years ago
- 记录NLP、CV、搜索、推荐等AI岗位最新情况。☆29Updated 2 years ago
- WoBERT_pytorch☆40Updated 4 years ago
- ☆39Updated 3 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 2 years ago
- BLOOM 模型的指令微调☆24Updated last year
- 中文soft-masked bert文本纠错复现☆21Updated 3 years ago
- CCL2022汉语学习者文本纠错评测任务赛道二——CGED-8第一名解决方案☆53Updated 2 years ago
- 多模型中文cnews新闻文本分类☆55Updated 5 years ago
- ☆12Updated last year
- The official repository for paper "LLMaAA: Making Large Language Models as Active Annotators"☆40Updated last year
- 基于prompt的中文文本分类。☆55Updated 2 years ago
- 基于中文 GPT2 预训练模型的文 本分类微调☆21Updated 2 years ago
- 天池算法比赛《BetterMixture - 大模型数据混合挑战赛》的第一名top1解决方案☆30Updated 10 months ago
- ☆57Updated 2 years ago
- GAIIC赛道一:影像学 NLP — 医学影像诊断报告生成 [A100换你大棚甜瓜 Rank-12 方案]☆66Updated last year
- 《Spelling Error Correction with Soft-Masked BERT》论文复现☆32Updated 3 years ago
- Code for Chinese grammatical error correction based on knowledge distillation☆11Updated 2 years ago
- Open source code for ICASSP 2021 Paper “Injecting Word Information with Multi-Level Word Adapter for Chinese Spoken Language Understandin…☆27Updated 4 years ago
- 中文文本纠错相关的论文、比赛和工具。☆55Updated last week
- 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 …☆28Updated 2 years ago