McGill-NLP / length-generalization
Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023
☆135Updated last year
Alternatives and similar repositories for length-generalization:
Users that are interested in length-generalization are comparing it to the libraries listed below
- Language models scale reliably with over-training and on downstream tasks☆96Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆80Updated 3 years ago
- ☆51Updated 11 months ago
- ☆159Updated 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 last year
- Randomized Positional Encodings Boost Length Generalization of Transformers☆81Updated last year
- ☆64Updated 8 months ago
- Code repository for the c-BTM paper☆106Updated last year
- ☆166Updated last year
- ☆45Updated last year
- Recurrent Memory Transformer☆149Updated last year
- Repository for the code of the "PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided Decoding" paper, NAACL'22☆65Updated 2 years ago
- [NeurIPS 2023] Learning Transformer Programs☆161Updated 11 months ago
- Simple and efficient pytorch-native transformer training and inference (batched)☆73Updated last year
- ☆72Updated last year
- Multipack distributed sampler for fast padding-free training of LLMs☆188Updated 8 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆72Updated 8 months ago
- ☆19Updated 2 years ago
- Efficient Transformers with Dynamic Token Pooling☆60Updated last year
- A framework for few-shot evaluation of autoregressive language models.☆24Updated last year
- Evaluation pipeline for the BabyLM Challenge 2023.☆75Updated last year
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated 2 years ago
- Token Omission Via Attention☆126Updated 6 months ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆65Updated 9 months ago
- Understand and test language model architectures on synthetic tasks.☆194Updated last month
- Code for Zero-Shot Tokenizer Transfer☆127Updated 3 months 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
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆105Updated this week
- Self-Alignment with Principle-Following Reward Models☆160Updated last year
- The original implementation of Min et al. "Nonparametric Masked Language Modeling" (paper https//arxiv.org/abs/2212.01349)☆157Updated 2 years ago