goombalab / phi-mambaLinks
Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models)
☆116Updated last year
Alternatives and similar repositories for phi-mamba
Users that are interested in phi-mamba are comparing it to the libraries listed below
Sorting:
- Some preliminary explorations of Mamba's context scaling.☆217Updated last year
- [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models☆229Updated 5 months ago
- Stick-breaking attention☆60Updated 3 months ago
- ☆85Updated last year
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆132Updated last week
- DeciMamba: Exploring the Length Extrapolation Potential of Mamba (ICLR 2025)☆31Updated 5 months ago
- M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models☆40Updated 2 months ago
- Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"☆159Updated 8 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆84Updated 11 months ago
- Mixture of A Million Experts☆48Updated last year
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆128Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆129Updated 9 months ago
- ☆53Updated last year
- Understand and test language model architectures on synthetic tasks.☆229Updated last week
- Official PyTorch Implementation of the Longhorn Deep State Space Model☆53Updated 10 months ago
- Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆106Updated this week
- ☆56Updated last year
- Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…☆98Updated last month
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆240Updated 3 months ago
- ☆35Updated 6 months ago
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆92Updated 9 months ago
- ☆101Updated 2 weeks ago
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆180Updated 3 months ago
- ☆302Updated 5 months ago
- ☆89Updated 7 months ago
- ☆104Updated last year
- Physics of Language Models, Part 4☆247Updated 2 months ago
- Griffin MQA + Hawk Linear RNN Hybrid☆89Updated last year
- The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink…☆81Updated 2 weeks ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆181Updated last year