nanowell / Differential-Transformer-PyTorch
PyTorch implementation of the Differential-Transformer architecture for sequence modeling, specifically tailored as a decoder-only model similar to large language models (LLMs). The architecture incorporates a novel Differential Attention mechanism, Multi-Head structure, RMSNorm, and SwiGLU.
☆43Updated 3 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for Differential-Transformer-PyTorch
- Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆50Updated last week
- ☆96Updated last week
- An open source community implementation of the model from "DIFFERENTIAL TRANSFORMER" paper by Microsoft.☆15Updated last week
- Minimal Mamba-2 implementation in PyTorch☆136Updated 5 months ago
- My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing o…☆41Updated 11 months ago
- A repository for DenseSSMs☆88Updated 7 months ago
- A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (http…☆100Updated 11 months ago
- Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling☆169Updated last week
- The open source implementation of the cross attention mechanism from the paper: "JOINTLY TRAINING LARGE AUTOREGRESSIVE MULTIMODAL MODELS"☆22Updated 8 months ago
- A Triton Kernel for incorporating Bi-Directionality in Mamba2☆50Updated 2 months ago
- Awesome list of papers that extend Mamba to various applications.☆128Updated 2 months ago
- ☆119Updated 6 months ago
- Simba☆182Updated 7 months ago
- Official PyTorch Implementation of "The Hidden Attention of Mamba Models"☆200Updated 5 months ago
- ☆181Updated 11 months ago
- State Space Models☆63Updated 6 months ago
- Implementation of Agent Attention in Pytorch☆86Updated 4 months ago
- PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"☆137Updated last week
- Implementation of MoE Mamba from the paper: "MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts" in Pytorch and Ze…☆84Updated last week
- First-principle implementations of groundbreaking AI algorithms using a wide range of deep learning frameworks, accompanied by supporting…☆70Updated this week
- Causal depthwise conv1d in CUDA, with a PyTorch interface☆329Updated 3 months ago
- The this is the official implementation of "DAPE: Data-Adaptive Positional Encoding for Length Extrapolation"☆32Updated last month
- An efficient pytorch implementation of selective scan in one file, works with both cpu and gpu, with corresponding mathematical derivatio…☆71Updated 8 months ago
- ☆77Updated 4 months ago
- ☆41Updated 7 months ago
- (Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from …☆133Updated 6 months ago
- ☆131Updated 2 months ago
- ☆25Updated last month
- RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks☆76Updated 3 months ago
- Implementation of Switch Transformers from the paper: "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficien…☆55Updated last week