HazyResearch / train-tk

Related projects ⓘ

Alternatives and complementary repositories for train-tk

• Edward-Sun / gpt-accelera
  Simple and efficient pytorch-native transformer training and inference (batched)
  ☆61Updated 7 months ago
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆72Updated 9 months ago
• ScalingIntelligence / large_language_monkeys
  ☆50Updated last month
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆104Updated last month
• EleutherAI / improved-t5
  Experiments for efforts to train a new and improved t5
  ☆76Updated 6 months ago
• mgmalek / efficient_cross_entropy
  ☆76Updated 5 months ago
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆95Updated 6 months ago
• cloneofsimo / min-fsdp
  ☆72Updated 4 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆84Updated last week
• dvruette / barrel-rec-pytorch
  ☆53Updated 9 months ago
• google-deepmind / asyncdiloco
  ☆39Updated 9 months ago
• MatX-inc / seqax
  seqax = sequence modeling + JAX
  ☆132Updated 3 months ago
• UmerHA / triton_util
  Make triton easier
  ☆41Updated 5 months ago
• berlino / seq_icl
  ☆50Updated 5 months ago
• euclaise / supertrainer2000
  ☆49Updated 7 months ago
• okarthikb / state-space-models
  ☆27Updated 4 months ago
• recursal / GoldFinch-paper
  GoldFinch and other hybrid transformer components
  ☆39Updated 3 months ago
• schwartz-lab-NLP / TOVA
  Token Omission Via Attention
  ☆119Updated 3 weeks ago
• xjdr-alt / muzero_sketch
  ☆36Updated 3 months ago
• joey00072 / ohara
  Collection of autoregressive model implementation
  ☆66Updated last week
• jxbz / modula
  Scalable neural net training via automatic normalization in the modular norm.
  ☆119Updated 2 months ago
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆40Updated last month
• AnswerDotAI / cold-compress
  Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…
  ☆86Updated 3 months ago
• HazyResearch / based
  Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"
  ☆213Updated 2 months ago
• NousResearch / StripedHyenaTrainer
  ☆55Updated 11 months ago
• RobertCsordas / moeut
  ☆61Updated 2 months ago
• drisspg / transformer_nuggets
  A place to store reusable transformer components of my own creation or found on the interwebs
  ☆43Updated last week
• KhoomeiK / complexity-scaling
  gzip Predicts Data-dependent Scaling Laws
  ☆32Updated 5 months ago
• cat-state / tinypar
  ☆20Updated last year
• KellerJordan / Muon
  Muon optimizer for neural networks: >30% extra sample efficiency, <3% wallclock overhead
  ☆69Updated this week