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.
  ☆359Updated this week
• idoh / mamba.np
  A pure NumPy implementation of Mamba.
  ☆219Updated 5 months ago
• explosion / curated-transformers
  🤖 A PyTorch library of curated Transformer models and their composable components
  ☆869Updated 8 months ago
• cabralpinto / modular-diffusion
  Python library for designing and training your own Diffusion Models with PyTorch.
  ☆267Updated 4 months ago
• jxbz / agd
  Automatic gradient descent
  ☆206Updated last year
• epistoteles / TensorHue
  TensorHue is a Python library that allows you to visualize tensors right in your console, making understanding and debugging tensor conte…
  ☆111Updated 2 months ago
• apple / ml-sigma-reparam
  ☆294Updated 5 months ago
• BlackHC / neural_net_checklist
  ☆140Updated 4 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…
  ☆603Updated 2 weeks ago
• srush / Transformer-Puzzles
  Puzzles for exploring transformers
  ☆327Updated last year
• facebookresearch / spdl
  Scalable and Performant Data Loading
  ☆184Updated this week
• google-deepmind / nanodo
  ☆199Updated 5 months ago
• fferflo / einx
  Universal Tensor Operations in Einstein-Inspired Notation for Python.
  ☆331Updated 2 weeks ago
• google-deepmind / synjax
  ☆242Updated 2 months ago
• HMUNACHI / nanodl
  A Jax-based library for designing and training transformer models from scratch.
  ☆278Updated 3 months ago
• srush / Autodiff-Puzzles
  ☆394Updated last month
• google-deepmind / recurrentgemma
  Open weights language model from Google DeepMind, based on Griffin.
  ☆612Updated 5 months ago
• mlecauchois / micrograd-cuda
  ☆235Updated 8 months ago
• srush / annotated-mamba
  Annotated version of the Mamba paper
  ☆460Updated 9 months ago
• srush / raspy
  An interactive exploration of Transformer programming.
  ☆253Updated last year
• 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…
  ☆341Updated 4 months ago
• stanford-crfm / levanter
  Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax
  ☆526Updated this week
• johnmarktaylor91 / torchlens
  Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.
  ☆490Updated last month
• bclarkson-code / Tricycle
  Autograd to GPT-2 completely from scratch
  ☆107Updated 4 months ago
• hristo-vrigazov / mmap.ninja
  Memory mapped numpy arrays of varying shapes
  ☆287Updated 5 months ago
• rentruewang / bocoel
  Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…
  ☆271Updated 2 weeks ago
• glassroom / heinsen_sequence
  Code implementing "Efficient Parallelization of a Ubiquitious Sequential Computation" (Heinsen, 2023)
  ☆88Updated last week
• facebookresearch / optimizers
  For optimization algorithm research and development.
  ☆464Updated this week
• RobertRiachi / nanoPALM
  ☆142Updated last year
• DiscoGrad / DiscoGrad
  DiscoGrad - automatically differentiate across conditional branches in C++ programs
  ☆204Updated 3 months ago