Alternatives and similar repositories for mad-lab

Users that are interested in mad-lab are comparing it to the libraries listed below

• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆219Updated last month
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆147Updated 3 weeks ago
• HazyResearch / based
  Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"
  ☆237Updated last month
• berlino / seq_icl
  ☆53Updated last year
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆100Updated 2 months ago
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆128Updated 7 months ago
• srush / do-we-need-attention
  ☆166Updated 2 years ago
• jzhang38 / LongMamba
  Some preliminary explorations of Mamba's context scaling.
  ☆215Updated last year
• llm-random / llm-random
  ☆191Updated last week
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆190Updated last year
• HazyResearch / lolcats
  Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"
  ☆244Updated 5 months ago
• epfml / dynamic-sparse-flash-attention
  ☆147Updated 2 years ago
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆184Updated 8 months ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆83Updated 7 months ago
• proger / accelerated-scan
  Accelerated First Order Parallel Associative Scan
  ☆182Updated 10 months ago
• insuhan / hyper-attn
  ☆81Updated last year
• MatX-inc / seqax
  seqax = sequence modeling + JAX
  ☆165Updated last month
• Edward-Sun / gpt-accelera
  Simple and efficient pytorch-native transformer training and inference (batched)
  ☆77Updated last year
• microsoft / mutransformers
  some common Huggingface transformers in maximal update parametrization (µP)
  ☆81Updated 3 years ago
• proger / hippogriff
  Griffin MQA + Hawk Linear RNN Hybrid
  ☆87Updated last year
• epfml / DenseFormer
  ☆81Updated last year
• cloneofsimo / min-fsdp
  ☆80Updated last year
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆77Updated 8 months ago
• shikaiqiu / compute-better-spent
  ☆53Updated 9 months ago
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆79Updated last year
• mgmalek / efficient_cross_entropy
  ☆112Updated last year
• mlfoundations / scaling
  Language models scale reliably with over-training and on downstream tasks
  ☆97Updated last year
• xiayuqing0622 / flex_head_fa
  Fast and memory-efficient exact attention
  ☆68Updated 4 months ago
• srush / mamba-primer
  ☆37Updated last year
• OpenEvaByte / evabyte
  EvaByte: Efficient Byte-level Language Models at Scale
  ☆103Updated 2 months ago