yikangshen / megablocksLinks
☆20Updated last year
Alternatives and similar repositories for megablocks
Users that are interested in megablocks are comparing it to the libraries listed below
Sorting:
- ☆31Updated last year
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆19Updated 2 years ago
- Implementation of the model: "Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models" in PyTorch☆29Updated last week
- Repository for Skill Set Optimization☆13Updated 10 months ago
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆17Updated last year
- Using FlexAttention to compute attention with different masking patterns☆43Updated 8 months ago
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"☆23Updated last month
- Minimum Description Length probing for neural network representations☆19Updated 4 months ago
- ☆54Updated 10 months ago
- ☆31Updated last year
- triton ver of gqa flash attn, based on the tutorial☆11Updated 10 months ago
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated last year
- ☆46Updated last year
- This repository contains the code and data for the paper "VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception o…☆23Updated 2 months ago
- Here we will test various linear attention designs.☆58Updated last year
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated 11 months ago
- ☆45Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆47Updated last year
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆35Updated last year
- PyTorch codes for the paper "An Empirical Study of Multimodal Model Merging"☆38Updated last year
- Blog post☆17Updated last year
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆50Updated 3 years ago
- Self-Supervised Alignment with Mutual Information☆18Updated last year
- Tasks for describing differences between text distributions.☆16Updated 9 months ago
- Efficient Scaling laws and collaborative pretraining.☆16Updated 4 months ago
- sigma-MoE layer☆18Updated last year
- ☆19Updated 10 months ago
- Codebase for Context-aware Meta-learned Loss Scaling (CaMeLS). https://arxiv.org/abs/2305.15076.☆25Updated last year
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free☆38Updated 3 weeks ago