Alternatives and similar repositories for compute-better-spent

Users that are interested in compute-better-spent are comparing it to the libraries listed below

• AndPotap / einsum-search
  ☆32Updated 11 months ago
• berlino / seq_icl
  ☆53Updated last year
• lucidrains / pause-transformer
  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
• lucidrains / gateloop-transformer
  Implementation of GateLoop Transformer in Pytorch and Jax
  ☆90Updated last year
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated 9 months ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆82Updated 10 months ago
• dvruette / barrel-rec-pytorch
  ☆53Updated last year
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆129Updated 9 months ago
• google-deepmind / spectral_ssm
  ☆34Updated last year
• epfml / DenseFormer
  ☆82Updated last year
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated last year
• johnryan465 / pscan
  ☆40Updated last year
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆88Updated last year
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆107Updated 4 months ago
• lucidrains / taylor-series-linear-attention
  Explorations into the recently proposed Taylor Series Linear Attention
  ☆100Updated last year
• cloneofsimo / min-fsdp
  ☆88Updated last year
• nikhilvyas / SOAP
  ☆210Updated 9 months ago
• edwardmilsom / function-space-learning-rates-paper
  Code for the paper "Function-Space Learning Rates"
  ☆23Updated 3 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆160Updated 2 months ago
• tml-epfl / why-weight-decay
  Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
  ☆67Updated 11 months ago
• proger / accelerated-scan
  Accelerated First Order Parallel Associative Scan
  ☆188Updated last year
• LIONS-EPFL / scion
  ☆39Updated last week
• martin-marek / batch-size
  📄Small Batch Size Training for Language Models
  ☆60Updated 3 weeks ago
• huyphan168 / PEER
  Mixture of A Million Experts
  ☆47Updated last year
• jopetty / word-problem
  Experiments on the impact of depth in transformers and SSMs.
  ☆33Updated 10 months ago
• apple / ml-ademamix
  ☆65Updated 10 months ago
• cloneofsimo / zeroshampoo
  ☆34Updated last year
• radarFudan / mamba-minimal-jax
  ☆34Updated 9 months ago
• proger / hippogriff
  Griffin MQA + Hawk Linear RNN Hybrid
  ☆89Updated last year
• dayal-kalra / low-memory-adam
  ☆12Updated 6 months ago