libeineu / ODE-TransformerLinks
This is a code repository for the ACL 2022 paper "ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation", which redesigns the Transformer architecture from the ODE perspective via using high-order ODE solvers to enhance the residual connections.
☆35Updated 3 years ago
Alternatives and similar repositories for ODE-Transformer
Users that are interested in ODE-Transformer are comparing it to the libraries listed below
Sorting:
- Learning to Encode Position for Transformer with Continuous Dynamical Model☆59Updated 5 years ago
- ☆29Updated 3 years ago
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆78Updated 2 years ago
- Language modeling via stochastic processes. Oral @ ICLR 2022.☆139Updated 2 years ago
- ☆52Updated 3 years ago
- A probabilitic model for contextual word representation. Accepted to ACL2023 Findings.☆25Updated 2 years ago
- Code for Residual Energy-Based Models for Text Generation in PyTorch.☆26Updated 4 years ago
- Offical code of the paper Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Le…☆75Updated last year
- FairSeq repo with Apollo optimizer☆114Updated 2 years ago
- Implementation for Variational Information Bottleneck for Effective Low-resource Fine-tuning, ICLR 2021☆43Updated 4 years ago
- Crawl & visualize ICLR papers and reviews.☆18Updated 3 years ago
- ☆46Updated 4 years ago
- Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data☆57Updated 4 years ago
- Dispersed Exponential Family Mixture VAE☆28Updated 5 years ago
- ☆37Updated last year
- ☆33Updated 4 years ago
- Methods and evaluation for aligning language models temporally☆30Updated last year
- Implementation of QKVAE☆11Updated 2 years ago
- Implementation of ICLR 21 paper: Probing BERT in Hyperbolic Spaces☆58Updated 4 years ago
- ☆31Updated 2 years ago
- EMNLP'2022: BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation☆41Updated 3 years ago
- [ICLR 2024]EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling(https://arxiv.org/abs/2310.04691)☆128Updated last year
- Code for paper Fully Hyperbolic Neural Networks☆87Updated 3 years ago
- Source code of LatentOps☆78Updated 2 years ago
- ☆15Updated 3 years ago
- [EMNLP 2022] Code for our paper “ZeroGen: Efficient Zero-shot Learning via Dataset Generation”.☆48Updated 3 years ago
- Princeton NLP's pre-training library based on fairseq with DeepSpeed kernel integration 🚃☆116Updated 3 years ago
- ☆17Updated 2 years ago
- No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models (ICLR 2022)☆29Updated 4 years ago
- ☆116Updated 3 years ago