Keras library for building (Universal) Transformers, facilitating BERT and GPT models
☆541May 30, 2020Updated 5 years ago
Alternatives and similar repositories for keras-transformer
Users that are interested in keras-transformer are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Keras+TensorFlow Implementation of the Transformer: Attention Is All You Need☆714Sep 24, 2021Updated 4 years ago
- Transformer implemented in Keras☆369Jan 22, 2022Updated 4 years ago
- Keras implementation of BERT with pre-trained weights☆815Jul 26, 2019Updated 6 years ago
- A wrapper layer for stacking layers horizontally☆228Jan 22, 2022Updated 4 years ago
- Attention mechanism for processing sequential data that considers the context for each timestamp.☆657Jan 22, 2022Updated 4 years ago
- DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Implementation of BERT that could load official pre-trained models for feature extraction and prediction☆2,426Jan 22, 2022Updated 4 years ago
- Transformer-XL with checkpoint loader☆67Jan 22, 2022Updated 4 years ago
- Adaptive embedding and softmax☆17Jan 22, 2022Updated 4 years ago
- Keras Attention Layer (Luong and Bahdanau scores).☆2,813Mar 12, 2026Updated 2 weeks ago
- Position embedding layers in Keras☆58Jan 22, 2022Updated 4 years ago
- Load GPT-2 checkpoint and generate texts☆127Jan 22, 2022Updated 4 years ago
- Re-implementation of ELMo on Keras☆135Mar 25, 2023Updated 3 years ago
- Keras library for building (Universal) Transformers, facilitating BERT and GPT models☆11Jan 29, 2019Updated 7 years ago
- XLNet: Generalized Autoregressive Pretraining for Language Understanding☆6,178May 28, 2023Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Collection of custom layers and utility functions for Keras which are missing in the main framework.☆62May 25, 2020Updated 5 years ago
- Visualizing RNNs using the attention mechanism☆750Jun 25, 2019Updated 6 years ago
- Keras community contributions☆1,584Oct 21, 2022Updated 3 years ago
- Super easy library for BERT based NLP models☆1,920Aug 19, 2024Updated last year
- some attention implements☆1,452Nov 20, 2019Updated 6 years ago
- Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includ…☆2,387Sep 3, 2024Updated last year
- An Attention Layer in Keras☆43Apr 23, 2019Updated 6 years ago
- A Keras TensorFlow 2.0 implementation of BERT, ALBERT and adapter-BERT.☆808Jan 13, 2023Updated 3 years ago
- attention block for keras Functional Model with only tensorflow backend☆26Apr 13, 2019Updated 6 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- keras implement of transformers for humans☆5,424Nov 11, 2024Updated last year
- Implementation of the Transformer architecture described by Vaswani et al. in "Attention Is All You Need"☆28Apr 21, 2019Updated 6 years ago
- Sequence to Sequence Learning with Keras☆3,176Aug 20, 2022Updated 3 years ago
- A simple technique to integrate BERT from tf hub to keras☆258Feb 15, 2023Updated 3 years ago
- Ordered Neurons LSTM☆30Jan 22, 2022Updated 4 years ago
- Neural Machine Translation with Keras☆531Jul 30, 2021Updated 4 years ago
- Tensorflow NCE loss in Keras☆34Oct 6, 2018Updated 7 years ago
- A Transformer implementation in Keras' Imperative (Subclassing) API for TensorFlow.☆55Aug 16, 2019Updated 6 years ago
- How to use ELMo embeddings in Keras with Tensorflow Hub☆260Dec 18, 2018Updated 7 years ago
- DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"☆1,611Aug 12, 2020Updated 5 years ago
- Keras Layer implementation of Attention for Sequential models☆444Mar 25, 2023Updated 3 years ago
- Layer normalization implemented in Keras☆60Jan 22, 2022Updated 4 years ago
- Implementation of Universal Transformer in Pytorch☆267Nov 19, 2018Updated 7 years ago
- Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.☆17,082Jun 2, 2023Updated 2 years ago
- A Lite BERT☆60Oct 28, 2019Updated 6 years ago
- BERT Extension in TensorFlow☆30Aug 29, 2019Updated 6 years ago