wbrickner / noise_stepLinks
noise_step: Training in 1.58b With No Gradient Memory
☆220Updated 7 months ago
Alternatives and similar repositories for noise_step
Users that are interested in noise_step are comparing it to the libraries listed below
Sorting:
- Decentralized RL Training at Scale☆403Updated this week
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆318Updated 9 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆103Updated 5 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆69Updated 3 months ago
- ☆118Updated 7 months ago
- Getting crystal-like representations with harmonic loss☆192Updated 4 months ago
- DeMo: Decoupled Momentum Optimization☆190Updated 8 months ago
- Exploring Applications of GRPO☆245Updated 3 weeks ago
- SIMD quantization kernels☆78Updated this week
- Gradient descent is cool and all, but what if we could delete it?☆104Updated this week
- Simple Transformer in Jax☆138Updated last year
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆344Updated 7 months ago
- look how they massacred my boy☆63Updated 9 months ago
- GRadient-INformed MoE☆264Updated 10 months ago
- ☆144Updated 8 months ago
- RWKV in nanoGPT style☆191Updated last year
- in this repository, i'm going to implement increasingly complex llm inference optimizations☆64Updated 2 months ago
- ☆134Updated 11 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆283Updated this week
- Normalized Transformer (nGPT)☆185Updated 8 months ago
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆267Updated 9 months ago
- PyTorch implementation of models from the Zamba2 series.☆184Updated 6 months ago
- Alex Krizhevsky's original code from Google Code☆195Updated 9 years ago
- Fast parallel LLM inference for MLX☆204Updated last year
- prime is a framework for efficient, globally distributed training of AI models over the internet.☆786Updated 2 months ago
- Inference of Mamba models in pure C☆189Updated last year
- smolLM with Entropix sampler on pytorch☆150Updated 9 months ago
- run paligemma in real time☆131Updated last year
- Dion optimizer algorithm☆193Updated this week
- 1.58 Bit LLM on Apple Silicon using MLX☆217Updated last year