HazyResearch / safariLinks
Convolutions for Sequence Modeling
☆885Updated 11 months ago
Alternatives and similar repositories for safari
Users that are interested in safari are comparing it to the libraries listed below
Sorting:
- Language Modeling with the H3 State Space Model☆519Updated last year
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆634Updated last year
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆961Updated last year
- Cramming the training of a (BERT-type) language model into limited compute.☆1,333Updated 11 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆1,005Updated 9 months ago
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"☆1,060Updated last year
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆550Updated 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.☆381Updated last year
- maximal update parametrization (µP)☆1,533Updated 10 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,113Updated last year
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆586Updated last week
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆643Updated 5 months ago
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆409Updated 5 months ago
- Annotated version of the Mamba paper☆484Updated last year
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,265Updated 5 months ago
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆582Updated 11 months ago
- Implementation of https://srush.github.io/annotated-s4☆497Updated 2 years ago
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆462Updated last year
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆456Updated last year
- Open weights language model from Google DeepMind, based on Griffin.☆640Updated this week
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆866Updated last year
- The repository for the code of the UltraFastBERT paper☆516Updated last year
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆514Updated 3 weeks ago
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆345Updated 10 months ago
- ☆412Updated last year
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆213Updated 9 months ago
- Automatic gradient descent☆207Updated last year
- ☆269Updated 10 months ago
- ☆534Updated last year
- 🤖 A PyTorch library of curated Transformer models and their composable components☆890Updated last year