francoisfleuret / picogptLinks
Minimal GPT (~350 lines with a simple task to test it)
☆63Updated 2 months ago
Alternatives and similar repositories for picogpt
Users that are interested in picogpt are comparing it to the libraries listed below
Sorting:
- The boundary of neural network trainability is fractal☆221Updated last year
- ☆215Updated last year
- A package for defining deep learning models using categorical algebraic expressions.☆61Updated last year
- Getting crystal-like representations with harmonic loss☆195Updated 9 months ago
- ☆162Updated 3 months ago
- Graph neural networks in JAX.☆68Updated last year
- ☆64Updated 11 months ago
- Because we don't want a jupyter notebook mess...☆61Updated 7 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆103Updated last year
- ☆45Updated 3 months ago
- Jax like function transformation engine but micro, microjax☆34Updated last year
- ☆76Updated last year
- A practical guide to diffusion models, implemented from scratch.☆242Updated last month
- Diffusion models in PyTorch☆124Updated this week
- ☆60Updated 3 years ago
- Jax Codebase for Evolutionary Strategies at the Hyperscale☆216Updated last month
- Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural netwo…☆75Updated 7 months ago
- The Official PyTorch Implementation of "Brain-like Variational Inference" (NeurIPS 2025 Paper)☆65Updated 2 months ago
- Code for the Fractured Entangled Representation Hypothesis position paper!☆221Updated 2 months ago
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources☆150Updated 4 months ago
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated last year
- ☆53Updated 2 years ago
- σ-GPT: A New Approach to Autoregressive Models☆70Updated last year
- Deep Networks Grok All the Time and Here is Why☆38Updated last year
- An implementation of PSGD Kron second-order optimizer for PyTorch☆98Updated 6 months ago
- Implementation of the proposed Spline-Based Transformer from Disney Research☆105Updated last year
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆174Updated 2 years ago
- Induce brain-like topographic structure in your neural networks☆71Updated 6 months ago
- ☆27Updated last year
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆191Updated 3 weeks ago