lucidrains / PEER-pytorchLinks
Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind
☆124Updated 9 months ago
Alternatives and similar repositories for PEER-pytorch
Users that are interested in PEER-pytorch are comparing it to the libraries listed below
Sorting:
- Mixture of A Million Experts☆45Updated 10 months ago
- Some preliminary explorations of Mamba's context scaling.☆212Updated last year
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆170Updated 5 months ago
- Implementation of Infini-Transformer in Pytorch☆111Updated 5 months ago
- Understand and test language model architectures on synthetic tasks.☆197Updated 2 months ago
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆97Updated 8 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆126Updated 3 weeks ago
- Griffin MQA + Hawk Linear RNN Hybrid☆86Updated last year
- Token Omission Via Attention☆126Updated 7 months ago
- ☆79Updated 9 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆234Updated 3 months ago
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆155Updated last month
- Normalized Transformer (nGPT)☆181Updated 6 months ago
- ☆190Updated this week
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆126Updated 6 months ago
- [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models☆221Updated last month
- A MAD laboratory to improve AI architecture designs 🧪☆116Updated 5 months ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆88Updated 11 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆52Updated 2 months ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆56Updated last year
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆167Updated 2 months ago
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆56Updated 2 weeks ago
- This is the official repository for the paper "Flora: Low-Rank Adapters Are Secretly Gradient Compressors" in ICML 2024.☆103Updated 11 months ago
- Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.☆98Updated last month
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆127Updated last year
- ☆78Updated 10 months ago
- EvaByte: Efficient Byte-level Language Models at Scale☆98Updated last month
- supporting pytorch FSDP for optimizers☆79Updated 5 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆100Updated 5 months ago
- A byte-level decoder architecture that matches the performance of tokenized Transformers.☆63Updated last year