zhihu / cuBERT
Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL
☆543Updated 4 years ago
Alternatives and similar repositories for cuBERT:
Users that are interested in cuBERT are comparing it to the libraries listed below
- Running BERT without Padding☆471Updated 3 years ago
- a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.☆1,515Updated last year
- Feel free to fine tune large BERT models with Multi-GPU and FP16 support.☆192Updated 5 years ago
- The score code of FastBERT (ACL2020)☆602Updated 3 years ago
- TensorFlow code and pre-trained models for BERT☆114Updated 5 years ago
- C++ model train&inference framework☆224Updated 5 years ago
- A Fast Muti-processing BERT-Inference System☆101Updated 2 years ago
- ⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).☆310Updated last year
- multi-gpu pre-training in one machine for BERT without horovod (Data Parallelism)☆172Updated 2 weeks ago
- ☆214Updated last year
- deepx_core是一个专注于张量计算/深度学习的基础库☆375Updated last year
- ☆251Updated 2 years ago
- BERT distillation(基于BERT的蒸馏实 验 )☆311Updated 4 years ago
- DeepCT and HDCT uses BERT to generate novel, context-aware bag-of-words term weights for documents and queries.☆319Updated 3 years ago
- A Lite Bert For Self-Supervised Learning Language Representations☆716Updated 4 years ago
- DeepLearning Framework Performance Profiling Toolkit☆285Updated 3 years ago
- ParaGen is a PyTorch deep learning framework for parallel sequence generation.☆186Updated 2 years ago
- ☆442Updated 2 years ago
- EasyTransfer is designed to make the development of transfer learning in NLP applications easier.☆862Updated 2 years ago
- Papers I have read, mainly about NLP. Welcome everyone to supplement in issue.☆256Updated 4 years ago
- cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information☆273Updated 2 years ago
- OneFlow models for benchmarking.☆105Updated 7 months ago
- ☆323Updated this week
- BERT for Multitask Learning☆546Updated last year
- a Fast, Flexible, Extensible and Easy-to-use NLP Large-scale Pretraining and Multi-task Learning Framework.☆183Updated 4 years ago
- LAMB Optimizer for Large Batch Training (TensorFlow version)☆120Updated 5 years ago
- embedx 是基于 c++ 开发的、完全自研的分布式 embedding 训练和推理框架。它目前支持 图模型、深度排序、召回模型和图与排序、图与召回的联合训练模型等☆304Updated 10 months ago
- Repository for the paper "Optimal Subarchitecture Extraction for BERT"☆472Updated 2 years ago
- A PyTorch-based model pruning toolkit for pre-trained language models☆386Updated last year
- Tensorflow Implementation of R-Net☆578Updated 6 years ago