FlorianDietz / comgra
A tool to analyze and debug neural networks in pytorch. Use a GUI to traverse the computation graph and view the data from many different angles at the click of a button.
☆287Updated 4 months ago
Alternatives and similar repositories for comgra:
Users that are interested in comgra are comparing it to the libraries listed below
- An interactive HTML pretty-printer for machine learning research in IPython notebooks.☆411Updated last week
- Open weights language model from Google DeepMind, based on Griffin.☆636Updated 2 months ago
- Puzzles for exploring transformers☆344Updated 2 years ago
- Automatic gradient descent☆207Updated last year
- Universal Tensor Operations in Einstein-Inspired Notation for Python.☆367Updated 3 weeks ago
- ☆150Updated 8 months ago
- A pure NumPy implementation of Mamba.☆222Updated 9 months ago
- ☆217Updated 9 months ago
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…☆607Updated last month
- ☆246Updated 7 months ago
- 🤖 A PyTorch library of curated Transformer models and their composable components☆885Updated last year
- A repository for log-time feedforward networks☆222Updated last year
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆345Updated 9 months ago
- Scalable and Performant Data Loading☆247Updated this week
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆204Updated 5 months ago
- ☆143Updated 2 years ago
- Language Modeling with the H3 State Space Model☆520Updated last year
- For optimization algorithm research and development.☆509Updated this week
- ☆301Updated 10 months ago
- 🧱 Modula software package☆188Updated last month
- Annotated version of the Mamba paper☆483Updated last year
- The AdEMAMix Optimizer: Better, Faster, Older.☆183Updated 7 months ago
- ☆430Updated 6 months ago
- A simple implimentation of Bayesian Flow Networks (BFN)☆240Updated last year
- Memory mapped numpy arrays of varying shapes☆297Updated 10 months ago
- TensorDict is a pytorch dedicated tensor container.☆920Updated this week
- Highly commented implementations of Transformers in PyTorch☆136Updated last year
- ☆241Updated last year
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆569Updated this week
- git extension for {collaborative, communal, continual} model development☆211Updated 5 months ago