Code for the paper "Query-Key Normalization for Transformers"
☆53Mar 6, 2021Updated 5 years ago
Alternatives and similar repositories for QKNorm
Users that are interested in QKNorm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆19Oct 9, 2022Updated 3 years ago
- ☆21Mar 15, 2023Updated 3 years ago
- ☆29May 4, 2024Updated 2 years ago
- Suite of 500 procedurally-generated NLP tasks to study language model adaptability☆21Jul 16, 2022Updated 3 years ago
- triton ver of gqa flash attn, based on the tutorial☆12Aug 4, 2024Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".☆34Jun 11, 2025Updated 11 months ago
- sigma-MoE layer☆21Jan 5, 2024Updated 2 years ago
- mPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models☆11Jan 19, 2024Updated 2 years ago
- ☆13Feb 7, 2023Updated 3 years ago
- ☆26Sep 15, 2022Updated 3 years ago
- ☆16May 14, 2024Updated 2 years ago
- [ICLR 2022] Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators☆26Jul 26, 2023Updated 2 years ago
- Implementation of Cascaded Head-colliding Attention (ACL'2021)☆11Sep 16, 2021Updated 4 years ago
- All-in-one repository for Fine-tuning & Pretraining (Large) Language Models☆15Mar 8, 2023Updated 3 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- (ACL-IJCNLP 2021) Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models.☆21Jul 13, 2022Updated 3 years ago
- add a Arg: label_smoothing for torch.nn.CrossEntropyLoss()☆14Jan 13, 2021Updated 5 years ago
- Official code for the NeurIPS25 paper "RAT: Bridging RNN Efficiencyand Attention Accuracy in Language Modeling" (https://arxiv.org/abs/25…☆24Dec 10, 2025Updated 5 months ago
- Implementation and experiments for Partially Supervised NER via Expected Entity Ratio in TACL 2022☆14Nov 7, 2022Updated 3 years ago
- [EMNLP 2023] Official implementation of the algorithm ETSC: Exact Toeplitz-to-SSM Conversion our EMNLP 2023 paper - Accelerating Toeplitz…☆14Oct 17, 2023Updated 2 years ago
- [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)☆34Aug 6, 2023Updated 2 years ago
- Linear Attention Sequence Parallelism (LASP)☆88Jun 4, 2024Updated last year
- ☆68Aug 29, 2024Updated last year
- ☆41Feb 12, 2019Updated 7 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆16Dec 9, 2023Updated 2 years ago
- ☆16Mar 22, 2023Updated 3 years ago
- Very deep VAEs in JAX/Flax☆47Jun 16, 2021Updated 4 years ago
- Release of the ConditionalQA dataset☆21Nov 2, 2021Updated 4 years ago
- The implementation of "The Kanerva Machine" with Pytorch and Pyro☆12Jun 14, 2018Updated 7 years ago
- ☆16Mar 13, 2023Updated 3 years ago
- TensorFlow implementation of the Traversal Network (TNet) architecture, presented in "Hard-Attention for Scalable Image Classification" (…☆17Jun 17, 2022Updated 3 years ago
- Anonymous ICLR Submission☆14Sep 25, 2019Updated 6 years ago
- PlaNet: Learning Latent Dynamics for Planning from Pixels☆10Feb 13, 2020Updated 6 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆22May 3, 2022Updated 4 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆49Jan 27, 2022Updated 4 years ago
- [NAACL 2024] A Framework aims to wisely initialize unseen subword embeddings in PLMs for efficient large-scale continued pretraining☆18Nov 26, 2023Updated 2 years ago
- Hugging Face RoBERTa with Flash Attention 2☆24Sep 14, 2025Updated 8 months ago
- A JAX nn library☆21Sep 9, 2025Updated 8 months ago
- ☆13Nov 29, 2017Updated 8 years ago
- Training and evaluation code for the paper "Headless Language Models: Learning without Predicting with Contrastive Weight Tying" (https:/…☆29Apr 17, 2024Updated 2 years ago