Alternatives and similar repositories for comgra

Users that are interested in comgra are comparing it to the libraries listed below

• google-deepmind / treescope
  An interactive HTML pretty-printer for machine learning research in IPython notebooks.
  ☆426Updated 3 months ago
• jxbz / agd
  Automatic gradient descent
  ☆208Updated 2 years ago
• cabralpinto / modular-diffusion
  Python library for designing and training your own Diffusion Models with PyTorch.
  ☆286Updated last month
• RobertRiachi / nanoPALM
  ☆143Updated 2 years ago
• idoh / mamba.np
  A pure NumPy implementation of Mamba.
  ☆223Updated last year
• HenryNdubuaku / nanodl
  A Jax-based library for building transformers, includes implementations of GPT, Gemma, LlaMa, Mixtral, Whisper, SWin, ViT and more.
  ☆290Updated 11 months ago
• apple / ml-sigma-reparam
  ☆307Updated last year
• eduardoleao052 / Autograd-from-scratch
  Documented and Unit Tested educational Deep Learning framework with Autograd from scratch.
  ☆120Updated last year
• BlackHC / neural_net_checklist
  ☆150Updated 11 months ago
• tysam-code / hlb-gpt
  Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…
  ☆350Updated last year
• srush / raspy
  An interactive exploration of Transformer programming.
  ☆267Updated last year
• srush / Transformer-Puzzles
  Puzzles for exploring transformers
  ☆356Updated 2 years ago
• EvanZhuang / MetaTree
  Official implementation of MetaTree: Learning a Decision Tree Algorithm with Transformers
  ☆112Updated 10 months ago
• sumo43 / loopvlm
  run paligemma in real time
  ☆131Updated last year
• johnmarktaylor91 / torchlens
  Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.
  ☆601Updated 5 months ago
• pbelcak / fastfeedforward
  A repository for log-time feedforward networks
  ☆223Updated last year
• explosion / curated-transformers
  🤖 A PyTorch library of curated Transformer models and their composable components
  ☆893Updated last year
• valine / training-hot-swap
  Pytorch script hot swap: Change code without unloading your LLM from VRAM
  ☆126Updated 3 months ago
• mlcommons / algorithmic-efficiency
  MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…
  ☆389Updated this week
• fferflo / einx
  Universal Tensor Operations in Einstein-Inspired Notation for Python.
  ☆392Updated 4 months ago
• r-three / git-theta
  git extension for {collaborative, communal, continual} model development
  ☆217Updated 8 months ago
• facebookresearch / optimizers
  For optimization algorithm research and development.
  ☆524Updated this week
• google-deepmind / synjax
  ☆247Updated last month
• valine / NeuralFlow
  Visualize the intermediate output of Mistral 7B
  ☆367Updated 6 months ago
• mlop-ai / mlop
  Next Generation Experimental Tracking for Machine Learning Operations
  ☆334Updated 2 months ago
• PaulPauls / llama3_interpretability_sae
  A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…
  ☆622Updated 4 months ago
• adamkarvonen / chess_llm_interpretability
  Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …
  ☆209Updated 8 months ago
• glassroom / heinsen_sequence
  Code implementing "Efficient Parallelization of a Ubiquitious Sequential Computation" (Heinsen, 2023)
  ☆94Updated 8 months ago
• Cerebras / gigaGPT
  a small code base for training large models
  ☆308Updated 3 months ago
• hristo-vrigazov / mmap.ninja
  Memory mapped numpy arrays of varying shapes
  ☆299Updated last year