xiangyangkan / faster-bert-as-serviceLinks
Using TensorRT and Triton Server to build BERT model as a service
☆13Updated 3 years ago
Alternatives and similar repositories for faster-bert-as-service
Users that are interested in faster-bert-as-service are comparing it to the libraries listed below
Sorting:
- TensorRT☆11Updated 4 years ago
- Bert TensorRT模型加速部署☆9Updated 3 years ago
- Minimal example of using a traced huggingface transformers model with libtorch☆35Updated 4 years ago
- ☆52Updated 4 years ago
- KuaiSearch PERKS☆11Updated 3 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 5 years ago
- rasa_chinese 的服务 package☆18Updated 3 years ago
- GLM (General Language Model)☆24Updated 3 years ago
- 一个非常高效的字符串匹配工具,支持正向/反向最大匹配分词和多模式字符串精确匹配☆17Updated last year
- 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 5 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☆13Updated 3 years ago
- Large-scale exact string matching tool☆17Updated 2 months ago
- lightweighted deep learning inference service framework☆39Updated 3 years ago
- aigc evals☆10Updated last year
- 百川Dynamic NTK-ALiBi的代码实现:无需微调即可推理更长文本☆47Updated last year
- Knowledge Graph based Question Answering benchmark.☆10Updated 5 years ago
- ☆14Updated last year
- Table2answer: Read the database and answer without SQL https://arxiv.org/abs/1902.04260☆14Updated 4 years ago
- 实体链接过程中的一些相关代码☆10Updated 6 years ago
- ☆27Updated 7 months ago
- pytorch版基于gpt+nezha的中文多轮Cdial☆11Updated 2 years ago
- machine reading comprehension with deep learning☆20Updated 7 years ago
- implement bert in pure c++☆36Updated 5 years ago
- ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化☆48Updated last year
- Using FasterTransformer for accelerating the predict speed of bert and roberta☆13Updated 5 years ago
- 根据维基百科历史编辑数据提取纠错语料。☆12Updated 3 years ago
- A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck☆10Updated 2 years ago
- How to export Hugging Face's 🤗 NLP Transformers models to ONNX and use the exported model with the appropriate Transformers pipeline.☆24Updated 3 years ago
- 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 4 years ago
- 用于生成文本纠错模型(如Gector)需要的大量数据。☆13Updated 2 years ago