shikaiqiu / compute-better-spentLinks
☆53Updated 10 months ago
Alternatives and similar repositories for compute-better-spent
Users that are interested in compute-better-spent are comparing it to the libraries listed below
Sorting:
- ☆32Updated 10 months ago
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated last year
- ☆34Updated 10 months ago
- Code for the paper "Function-Space Learning Rates"☆23Updated 2 months ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆89Updated last year
- supporting pytorch FSDP for optimizers☆84Updated 8 months ago
- 📄Small Batch Size Training for Language Models☆41Updated this week
- ☆53Updated last year
- ☆33Updated last year
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- ☆81Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆81Updated 9 months ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆85Updated last year
- ☆83Updated last year
- ☆53Updated last year
- nanoGPT-like codebase for LLM training☆102Updated 2 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆149Updated last month
- Experiment of using Tangent to autodiff triton☆80Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆123Updated 7 months ago
- ☆33Updated 3 weeks ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆66Updated 10 months ago
- Official code for the paper "Attention as a Hypernetwork"☆40Updated last year
- ☆206Updated 8 months ago
- A State-Space Model with Rational Transfer Function Representation.☆79Updated last year
- Griffin MQA + Hawk Linear RNN Hybrid☆88Updated last year
- ☆81Updated last year
- Here we will test various linear attention designs.☆62Updated last year
- Deep Networks Grok All the Time and Here is Why☆37Updated last year
- Parallelizing non-linear sequential models over the sequence length☆53Updated last month
- ☆49Updated last year