sap-ient-ai / FFFLinks
FastFeedForward Networks
☆20Updated last year
Alternatives and similar repositories for FFF
Users that are interested in FFF are comparing it to the libraries listed below
Sorting:
- ☆82Updated last year
- ☆53Updated last year
- ☆28Updated last year
- ☆27Updated last year
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 2 months ago
- Jax like function transformation engine but micro, microjax☆33Updated 10 months ago
- ☆101Updated last month
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆129Updated 8 months ago
- GoldFinch and other hybrid transformer components☆46Updated last year
- H-Net Dynamic Hierarchical Architecture☆79Updated last month
- ☆49Updated last year
- Memoria is a human-inspired memory architecture for neural networks.☆75Updated 10 months ago
- ☆61Updated last year
- Token Omission Via Attention☆128Updated 10 months ago
- Codes accompanying the paper "LaProp: a Better Way to Combine Momentum with Adaptive Gradient"☆29Updated 5 years ago
- train with kittens!☆62Updated 10 months ago
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆46Updated last year
- ☆34Updated last year
- Experiment of using Tangent to autodiff triton☆80Updated last year
- RWKV model implementation☆38Updated 2 years ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆101Updated 8 months ago
- Automatically take good care of your preemptible TPUs☆36Updated 2 years ago
- Implementation of Spectral State Space Models☆16Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jax☆90Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Updated last month
- Experiments for efforts to train a new and improved t5☆76Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆87Updated last year
- ☆46Updated last year
- RWKV-7: Surpassing GPT☆94Updated 9 months ago
- HomebrewNLP in JAX flavour for maintable TPU-Training☆50Updated last year