lucidrains / memorizing-transformers-pytorch
Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch
☆622Updated last year
Related projects: ⓘ
- Language Modeling with the H3 State Space Model☆509Updated 11 months ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆850Updated 10 months ago
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆391Updated 7 months ago
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"☆1,049Updated 6 months ago
- Convolutions for Sequence Modeling☆861Updated 3 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,022Updated 8 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆957Updated 3 weeks ago
- Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"☆424Updated last year
- Cramming the training of a (BERT-type) language model into limited compute.☆1,284Updated 3 months ago
- Code for the ALiBi method for transformer language models (ICLR 2022)☆499Updated 10 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆408Updated 3 months ago
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆615Updated this week
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆202Updated 3 weeks ago
- Fast and flexible reference benchmarks☆435Updated last month
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆545Updated 2 months ago
- A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick☆283Updated 9 months ago
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆423Updated last year
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways☆819Updated last year
- Used for adaptive human in the loop evaluation of language and embedding models.☆300Updated last year
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆267Updated last month
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆222Updated last week
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆423Updated 7 months ago
- ☆453Updated 11 months ago
- ☆495Updated 7 months ago
- ☆243Updated last year
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆278Updated 3 months ago
- Implementation of Block Recurrent Transformer - Pytorch☆211Updated 3 weeks ago
- ☆409Updated 10 months ago
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆530Updated 3 months ago
- Sequence modeling with Mega.☆296Updated last year