proger / hippogriff
Griffin MQA + Hawk Linear RNN Hybrid
β85Updated 10 months ago
Alternatives and similar repositories for hippogriff:
Users that are interested in hippogriff are comparing it to the libraries listed below
- Understand and test language model architectures on synthetic tasks.β183Updated last week
- A MAD laboratory to improve AI architecture designs π§ͺβ107Updated 2 months ago
- Implementation of GateLoop Transformer in Pytorch and Jaxβ87Updated 8 months ago
- β51Updated 9 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmindβ121Updated 6 months ago
- Implementation of Infini-Transformer in Pytorchβ109Updated 2 months ago
- β73Updated 6 months ago
- Explorations into the recently proposed Taylor Series Linear Attentionβ94Updated 6 months ago
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Seβ¦β64Updated 10 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"β223Updated 3 weeks ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonettoβ55Updated 9 months ago
- Here we will test various linear attention designs.β59Updated 10 months ago
- Randomized Positional Encodings Boost Length Generalization of Transformersβ79Updated 11 months ago
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"β96Updated 5 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"β36Updated last year
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Ruleβ138Updated 2 weeks ago
- Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Modeβ¦β98Updated 5 months ago
- A single repo with all scripts and utils to train / fine-tune the Mamba model with or without FIMβ53Updated 11 months ago
- Stick-breaking attentionβ48Updated this week
- Some preliminary explorations of Mamba's context scaling.β213Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.β99Updated 3 months ago
- β52Updated 5 months ago
- Fast and memory-efficient exact attentionβ66Updated last week
- β47Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clustersβ123Updated 3 months ago
- GoldFinch and other hybrid transformer componentsβ44Updated 7 months ago
- This repo is based on https://github.com/jiaweizzhao/GaLoreβ26Updated 5 months ago
- A byte-level decoder architecture that matches the performance of tokenized Transformers.β64Updated 10 months ago