xiangyangkan / faster-bert-as-service
Using TensorRT and Triton Server to build BERT model as a service
☆12Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for faster-bert-as-service
- TensorRT☆11Updated 4 years ago
- Bert TensorRT模型加速部署☆9Updated 2 years ago
- KuaiSearch PERKS☆11Updated 2 years ago
- 基于电商导购机器人,自然语言理解(NLU),文本纠错,歧义词消歧☆12Updated 4 years ago
- lightweighted deep learning inference service framework☆38Updated 3 years ago
- Using FasterTransformer for accelerating the predict speed of bert and roberta☆13Updated 5 years ago
- 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
- rasa_chinese 的服务 package☆18Updated 3 years ago
- ☆52Updated 3 years ago
- Minimal example of using a traced huggingface transformers model with libtorch☆35Updated 4 years ago
- 针对NER领域提供从线下训练到线上部署的一整套闭环流程☆12Updated 3 years ago
- 记录有用的Git repos☆10Updated 3 months ago
- 全球人工智能技术创新大赛-赛道三:小布助手对话短文本语义匹配☆11Updated 3 years ago
- All code of tensorflow☆7Updated last year
- GLM (General Language Model)☆24Updated 2 years ago
- 基于BERT的预训练语言模型实现,分为两步:预训练和微调。目前已包括BERT、Roberta、ALbert三个模型,且皆可支持Whole Word Mask模式。☆16Updated 4 years ago
- Large-scale exact string matching tool☆15Updated last year
- 利用tensorflow/serving进行单模型、多模型、同一模型多版本的部署,并进行模型预测,并用Prothemus进行服务监控。☆11Updated 3 years ago
- 用于生成文本纠错模型(如Gector)需要的大量数据。☆14Updated last year
- implement bert in pure c++☆31Updated 4 years ago
- Source code and checkpoints for legal pre-trained language models.☆15Updated 3 years ago
- Finetune CPM-1☆24Updated 3 years ago
- 基于 onnxruntime 推理引擎的中文 ltp 词法分析☆13Updated 2 years ago
- ☆13Updated 4 years ago
- aigc evals☆10Updated 11 months ago
- 实体链接过程中的一些相关代码☆11Updated 6 years ago
- CLUE Emotion Analysis Dataset 细粒度情感分析数据集☆8Updated 4 years ago
- pytorch版基于gpt+nezha的中文多轮Cdial☆11Updated 2 years ago
- ☆15Updated 3 years ago