McGill-NLP / length-generalizationLinks
Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023
☆137Updated last year
Alternatives and similar repositories for length-generalization
Users that are interested in length-generalization are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2023] Learning Transformer Programs☆162Updated last year
- ☆45Updated 2 years ago
- ☆77Updated last year
- Language models scale reliably with over-training and on downstream tasks☆99Updated last year
- Repository for the code of the "PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided Decoding" paper, NAACL'22☆66Updated 3 years ago
- some common Huggingface transformers in maximal update parametrization (µP)☆87Updated 3 years ago
- Randomized Positional Encodings Boost Length Generalization of Transformers☆82Updated last year
- Code repository for the c-BTM paper☆108Updated 2 years ago
- ☆67Updated last year
- Efficient Transformers with Dynamic Token Pooling☆67Updated 2 years ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆78Updated last year
- Code for Zero-Shot Tokenizer Transfer☆142Updated last year
- ☆38Updated last year
- ☆158Updated 2 years ago
- Evaluation pipeline for the BabyLM Challenge 2023.☆77Updated 2 years ago
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated 2 years ago
- A repository for transformer critique learning and generation☆89Updated 2 years ago
- ☆72Updated 2 years ago
- This is the implementation of the paper AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning (https://arxiv.org/abs/2205.1…☆136Updated 2 years ago
- Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE …☆116Updated last year
- ☆53Updated last year
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆116Updated 2 years ago
- ☆44Updated last year
- ☆53Updated 2 years ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆75Updated last year
- Recurrent Memory Transformer☆155Updated 2 years ago
- ☆56Updated 2 years ago
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆81Updated 2 years ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆45Updated 4 months ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated 2 years ago