ericperfect / libtorch_tokenizer
BERT Tokenizer in C++
☆74Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for libtorch_tokenizer
- 高性能文本 Tokenizer 库☆27Updated 9 months ago
- Minimal example of using a traced huggingface transformers model with libtorch☆35Updated 4 years ago
- Finetune Bloom big language model with Lora method☆28Updated last year
- 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
- implement bert in pure c++☆32Updated 4 years ago
- 中文版unilm预训练模型☆82Updated 3 years ago
- lightweighted deep learning inference service framework☆38Updated 3 years ago
- Chinese MobileBERT（中文MobileBERT模型）☆81Updated 2 years ago
- 基于mlm方式的带有纠错功能的拼音转汉字bert预训练模型，pinyin correcter，基于pytorch框架实现☆45Updated 4 years ago
- Use bert to predict punctuation on IWSLT2012 and The People's Daily 2014☆65Updated 4 years ago
- Using FasterTransformer for accelerating the predict speed of bert and roberta☆13Updated 5 years ago
- C++ model train&inference framework☆223Updated 4 years ago
- tensorflow version of bert-of-theseus☆63Updated 3 years ago
- Python toolkit for Chinese Language Understanding(CLUE) Evaluation benchmark☆128Updated last year
- 拼音转汉字, convert pinyin to 汉字 using deep networks☆22Updated 4 years ago
- ☆51Updated 4 years ago
- 不用tensorflow estimator，分别采用字mask和wwm mask在中文领域内finetune bert模型☆23Updated 4 years ago
- ☆100Updated 4 years ago
- ☆52Updated 3 years ago
- Correcting Chinese Spelling Errors with Phonetic Pre-training 非官方实现☆38Updated 2 years ago
- soft_mask_bert model for Chinese Spelling Correction in keras☆21Updated 4 years ago
- 基于Pytorch 1.0 实现的中文断句与标点符号恢复。☆55Updated 5 years ago
- 离线端阅读理解应用 QA for mobile, Android & iPhone☆60Updated 2 years ago
- 大规模中文语料☆38Updated 5 years ago
- ☆74Updated 2 years ago
- TensorRT☆11Updated 4 years ago
- source code of EMNLP2021: A Lightweight Pretrained Model for Chinese Spelling Check☆13Updated 3 years ago
- ☆90Updated last year
- 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