IDEA-CCNL / fs_datasets
☆11Updated last year
Related projects ⓘ
Alternatives and complementary repositories for fs_datasets
- 有一个通用实体关系事件抽取的任务,需要使用到UIE模框架,而且需要将起部署到昇腾310服务器上,因为UIE模型底层使用的是ernie3.0,但是目前paddle官方还不支持ernie3.0模型在昇腾310上部署,所以才有了以下的操作,主要过程是,先试用paddle训练处模型…☆17Updated 2 years ago
- RDrop 的 torch版☆15Updated 3 years ago
- ☆9Updated last year
- benchmark of KgCLUE, with different models and methods☆26Updated 2 years ago
- FinCUGE Instruction dataset☆10Updated last year
- 基于PaddleNLP开源的抽取式UIE进行医学命名实体识别(torch实现)☆42Updated 2 years ago
- Using the model Efficient Global Pointer for Keyword extraction☆8Updated last year
- Topic Extraction baseline for Dialogue Text Analysis Task of nlpcc 2022☆13Updated 2 years ago
- 使用GENIUS文本生成模型训练自己的数据集。☆8Updated last year
- moss chat finetuning☆50Updated 7 months ago
- ☆10Updated 2 years ago
- ☆13Updated 4 years ago
- ☆13Updated 10 months ago
- 本项目采用BERT等预训练模型实现多项选择型阅读理解任务(Multiple Choice MRC)☆15Updated 3 years ago
- Sentence-Transformers Information Retrieval example on Chinese☆29Updated 9 months ago
- LLM+RAG for QA☆20Updated 10 months ago
- Chinese Grammatical Error Diagnosis☆11Updated 3 years ago
- 论文模型复现☆42Updated 2 years ago
- The very easy BERT pretrain process by using tokenizers and transformers repos☆31Updated 4 years ago
- 基于Roformer的文本相似度☆12Updated 3 years ago
- deep training task☆29Updated last year
- 中文bigbird预训练模型☆89Updated 2 years ago
- tf&torch about nlp☆10Updated 2 years ago
- 用Paddle复现论文ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information(ACL2021)☆9Updated 3 years ago
- ☆57Updated last year
- ☆13Updated 2 years ago
- Let ChatGPT (Large Language Models) Serve As Data Annotator and Zero-shot/few-shot Information Extractor.☆29Updated last year
- Efficient-GlobalPointer的关系抽取任务☆22Updated 2 years ago
- 百川Dynamic NTK-ALiBi的代码实现:无需微调即可推理更长文本☆46Updated last year