HazyResearch / safariLinks
Convolutions for Sequence Modeling
☆891Updated last year
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 MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆644Updated 6 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆1,004Updated 10 months ago
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆962Updated last year
- 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
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆634Updated last year
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆409Updated 5 months ago
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"☆1,060Updated last year
- The repository for the code of the UltraFastBERT paper☆516Updated last year
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆554Updated 6 months ago
- Annotated version of the Mamba paper☆485Updated last year
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,115Updated last year
- Cramming the training of a (BERT-type) language model into limited compute.☆1,336Updated last year
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆587Updated 11 months ago
- Automatic gradient descent☆208Updated 2 years ago
- Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"☆707Updated last year
- ☆415Updated last year
- ☆538Updated last year
- ☆458Updated 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…☆345Updated 11 months ago
- 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…☆1,573Updated last year
- Open weights language model from Google DeepMind, based on Griffin.☆643Updated 3 weeks ago
- Implementation of Block Recurrent Transformer - Pytorch☆219Updated 10 months ago
- ☆543Updated 6 months ago
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆214Updated 10 months ago
- ☆781Updated 3 weeks ago
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways☆823Updated 2 years ago
- maximal update parametrization (µP)☆1,549Updated 11 months ago
- [NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.☆763Updated 8 months ago
- ☆356Updated last year