McGill-NLP / length-generalization
Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023
☆129Updated 8 months ago
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 9 months 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…☆51Updated last year
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆42Updated last year
- ☆51Updated 7 months ago
- ☆44Updated last year
- Randomized Positional Encodings Boost Length Generalization of Transformers☆79Updated 10 months ago
- Code for Zero-Shot Tokenizer Transfer☆119Updated this week
- Efficient Transformers with Dynamic Token Pooling☆55Updated last year
- Code repository for the c-BTM paper☆105Updated last year
- ☆161Updated last year
- Recurrent Memory Transformer☆148Updated last year
- This is the implementation of the paper AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning (https://arxiv.org/abs/2205.1…☆127Updated last year
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆61Updated 5 months ago
- some common Huggingface transformers in maximal update parametrization (µP)☆78Updated 2 years ago
- Multipack distributed sampler for fast padding-free training of LLMs☆184Updated 5 months ago
- ☆113Updated 2 months ago
- [AAAI 2024] Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following☆79Updated 4 months ago
- A framework for few-shot evaluation of autoregressive language models.☆24Updated last year
- ☆78Updated 3 months ago
- ☆72Updated 8 months ago
- ☆125Updated last month
- A MAD laboratory to improve AI architecture designs 🧪☆102Updated last month
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆89Updated 3 years ago
- Understand and test language model architectures on synthetic tasks.☆175Updated this week
- [NeurIPS 2023] Learning Transformer Programs☆157Updated 7 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆219Updated last month
- A toolkit for scaling law research ⚖☆43Updated last month
- ☆18Updated 2 years ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆42Updated last year
- ☆96Updated last year