francoisfleuret / picogptLinks
Minimal GPT (~350 lines with a simple task to test it)
☆63Updated last month
Alternatives and similar repositories for picogpt
Users that are interested in picogpt are comparing it to the libraries listed below
Sorting:
- ☆214Updated last year
- The boundary of neural network trainability is fractal☆221Updated last year
- Getting crystal-like representations with harmonic loss☆194Updated 9 months ago
- ☆53Updated last year
- An implementation of PSGD Kron second-order optimizer for PyTorch☆97Updated 5 months ago
- ☆27Updated 3 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆103Updated last year
- ☆44Updated 2 months ago
- σ-GPT: A New Approach to Autoregressive Models☆70Updated last year
- A practical guide to diffusion models, implemented from scratch.☆232Updated last week
- ☆27Updated last year
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 11 months ago
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources☆149Updated 3 months ago
- ☆75Updated last year
- ☆82Updated last year
- Jax like function transformation engine but micro, microjax☆34Updated last year
- ☆34Updated last year
- ☆158Updated 2 months ago
- ☆21Updated last year
- Deep Networks Grok All the Time and Here is Why☆38Updated last year
- ☆60Updated 3 years ago
- A package for defining deep learning models using categorical algebraic expressions.☆61Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- H-Net Dynamic Hierarchical Architecture☆80Updated 4 months ago
- A basic pure pytorch implementation of flash attention☆16Updated last year
- ☆56Updated last year
- Code for the paper "Function-Space Learning Rates"☆23Updated 7 months ago
- Graph neural networks in JAX.☆68Updated last year
- ☆62Updated last year
- Diffusion models in PyTorch☆120Updated this week