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.
  ☆105Updated this week
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆189Updated 11 months ago
• google-deepmind / mishax
  ☆130Updated last month
• cloneofsimo / scaling-guide
  WIP
  ☆93Updated 8 months ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆123Updated last year
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆113Updated 4 months ago
• lucidrains / coconut-pytorch
  Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch
  ☆165Updated 4 months ago
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆194Updated 2 months ago
• jerber / lang-jepa
  ☆109Updated 4 months ago
• cloneofsimo / min-fsdp
  ☆78Updated 10 months ago
• Pleias / Quest-Best-Tokens
  An introduction to LLM Sampling
  ☆77Updated 4 months ago
• BlackHC / neural_net_checklist
  ☆150Updated 8 months ago
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).
  ☆224Updated last week
• idiap / sigma-gpt
  σ-GPT: A New Approach to Autoregressive Models
  ☆63Updated 8 months ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆80Updated 4 months ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆72Updated 6 months ago
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆172Updated 3 months ago
• fal-ai / diffusion-speedrun
  Focused on fast experimentation and simplicity
  ☆71Updated 4 months ago
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆94Updated last month
• modula-systems / modula
  🧱 Modula software package
  ☆188Updated last month
• epfml / DenseFormer
  ☆80Updated last year
• facebookresearch / capi
  Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
  ☆101Updated 3 weeks ago
• minyoungg / LTE
  ☆67Updated 9 months ago
• evanatyourservice / kron_torch
  An implementation of PSGD Kron second-order optimizer for PyTorch
  ☆89Updated last month
• joey00072 / ohara
  Collection of autoregressive model implementation
  ☆85Updated last week
• fangyuan-ksgk / Tiny-GRPO
  minimal GRPO implementation from scratch
  ☆87Updated last month
• RobertCsordas / moeut
  ☆78Updated 8 months ago
• OpenEvaByte / evabyte
  EvaByte: Efficient Byte-level Language Models at Scale
  ☆91Updated 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
  ☆123Updated 8 months ago
• allenai / infinigram-api
  ☆54Updated this week