SHI-Labs / CompactNet
☆31Updated 9 months ago
Alternatives and similar repositories for CompactNet:
Users that are interested in CompactNet are comparing it to the libraries listed below
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆36Updated last year
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆23Updated last month
- ☆31Updated 10 months ago
- ☆33Updated 5 months ago
- ☆52Updated 4 months ago
- ☆30Updated 2 months ago
- ☆26Updated last month
- Triton Implementation of HyperAttention Algorithm☆46Updated last year
- Minimal Implementation of Visual Autoregressive Modelling (VAR)☆26Updated last month
- ☆71Updated 6 months ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆25Updated 10 months ago
- Source code for the paper "Positional Attention: Out-of-Distribution Generalization and Expressivity for Neural Algorithmic Reasoning"☆14Updated 3 weeks ago
- Efficient PScan implementation in PyTorch☆15Updated last year
- ☆21Updated 3 months ago
- ☆37Updated 10 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆17Updated last week
- Unofficial Implementation of Selective Attention Transformer☆15Updated 3 months ago
- Efficient Scaling laws and collaborative pretraining.☆14Updated 3 weeks ago
- Here we will test various linear attention designs.☆58Updated 9 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆70Updated 3 months ago
- ☆23Updated last year
- Utilities for PyTorch distributed☆23Updated last year
- Official code for the paper "Attention as a Hypernetwork"☆23Updated 7 months ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆60Updated 4 months ago
- ☆53Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆52Updated 6 months ago
- Towards Understanding the Mixture-of-Experts Layer in Deep Learning☆22Updated last year
- Implementation of Spectral State Space Models☆16Updated 11 months ago
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆24Updated 3 months ago