Alternatives and similar repositories for academic-pretraining:

Users that are interested in academic-pretraining are comparing it to the libraries listed below

• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆90Updated last month
• modula-systems / modula
  🧱 Modula software package
  ☆132Updated this week
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆182Updated 7 months ago
• cloneofsimo / scaling-guide
  WIP
  ☆92Updated 5 months ago
• RobertCsordas / moeut
  ☆69Updated 4 months ago
• cloneofsimo / min-fsdp
  ☆75Updated 6 months ago
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆102Updated last month
• idiap / sigma-gpt
  σ-GPT: A New Approach to Autoregressive Models
  ☆61Updated 5 months ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆75Updated last month
• google-deepmind / mishax
  ☆115Updated this week
• dvruette / barrel-rec-pytorch
  ☆53Updated 11 months ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆66Updated 2 months ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆121Updated 9 months ago
• EleutherAI / sae-auto-interp
  ☆135Updated this week
• ltgoslo / bert-in-context
  Official implementation of "BERTs are Generative In-Context Learners"
  ☆23Updated 7 months ago
• joey00072 / ohara
  Collection of autoregressive model implementation
  ☆76Updated last week
• nikhilvyas / SOAP
  ☆146Updated last month
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆175Updated this week
• ml-jku / EVA
  One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation
  ☆36Updated 3 months ago
• jonhue / activeft
  PyTorch library for Active Fine-Tuning
  ☆52Updated last week
• lucidrains / coconut-pytorch
  Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch
  ☆145Updated 2 weeks ago
• hyperevolnet / Terminator
  The official repository for HyperZ⋅Z⋅W Operator Connects Slow-Fast Networks for Full Context Interaction.
  ☆31Updated this week
• riverstone496 / awesome-second-order-optimization
  ☆25Updated last year
• bloc97 / DeMo
  DeMo: Decoupled Momentum Optimization
  ☆170Updated last month
• mlfoundations / evalchemy
  Automatic Evals for Instruction-Tuned Models
  ☆100Updated this week
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆157Updated this week
• jerber / lang-jepa
  ☆96Updated 3 weeks ago
• Pleias / Quest-Best-Tokens
  An introduction to LLM Sampling
  ☆75Updated last month
• koayon / awesome-adaptive-computation
  A curated reading list of research in Adaptive Computation, Inference-Time Computation & Mixture of Experts (MoE).
  ☆136Updated 2 weeks ago
• lucidrains / PEER-pytorch
  Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind
  ☆115Updated 4 months ago