HazyResearch / safari
Convolutions for Sequence Modeling
☆877Updated 10 months ago
Alternatives and similar repositories for safari:
Users that are interested in safari are comparing it to the libraries listed below
- Language Modeling with the H3 State Space Model☆520Updated last year
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆407Updated 3 months ago
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆632Updated last year
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆957Updated last year
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆641Updated 3 months ago
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆549Updated 3 months ago
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"☆1,060Updated last year
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆380Updated 10 months ago
- Annotated version of the Mamba paper☆483Updated last year
- Implementation of https://srush.github.io/annotated-s4☆490Updated 2 years ago
- Implementation of Block Recurrent Transformer - Pytorch☆217Updated 8 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆1,001Updated 8 months ago
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆576Updated 9 months ago
- Cramming the training of a (BERT-type) language model into limited compute.☆1,331Updated 10 months ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆863Updated last year
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆458Updated last year
- Sequence modeling with Mega.☆294Updated 2 years ago
- ☆531Updated last year
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,101Updated last year
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆226Updated 7 months ago
- The repository for the code of the UltraFastBERT paper☆518Updated last year
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆211Updated 8 months ago
- 🤖 A PyTorch library of curated Transformer models and their composable components☆884Updated last year
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆377Updated last year
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆568Updated this week
- A repository for log-time feedforward networks☆221Updated last year
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆452Updated last year
- Automatic gradient descent☆207Updated last year
- A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick☆289Updated last year
- Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"☆704Updated last year