HazyResearch / safari
Convolutions for Sequence Modeling
☆867Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for safari
- Language Modeling with the H3 State Space Model☆513Updated last year
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆625Updated last year
- Cramming the training of a (BERT-type) language model into limited compute.☆1,295Updated 4 months ago
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆937Updated 9 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆968Updated 2 months ago
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆624Updated last month
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"☆1,053Updated 8 months ago
- maximal update parametrization (µP)☆1,398Updated 3 months ago
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆393Updated 8 months ago
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆536Updated 5 months ago
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆377Updated 5 months ago
- Annotated version of the Mamba paper☆455Updated 8 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,041Updated 9 months ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆851Updated last year
- ☆411Updated last year
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆550Updated 4 months ago
- Implementation of https://srush.github.io/annotated-s4☆468Updated last year
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…☆1,532Updated 8 months ago
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆712Updated 2 months ago
- Open weights language model from Google DeepMind, based on Griffin.☆606Updated 4 months ago
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆433Updated 6 months ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,223Updated last year
- Repository for StripedHyena, a state-of-the-art beyond Transformer architecture☆267Updated 8 months ago
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆332Updated 3 months ago
- ☆527Updated 9 months ago
- ☆506Updated 9 months ago
- A simple and effective LLM pruning approach.☆660Updated 3 months ago
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆224Updated 2 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…☆2,401Updated 2 months ago