main-horse / hnetLinks
H-Net Dynamic Hierarchical Architecture
☆79Updated last month
Alternatives and similar repositories for hnet
Users that are interested in hnet are comparing it to the libraries listed below
Sorting:
- NanoGPT-speedrunning for the poor T4 enjoyers☆69Updated 4 months ago
- ☆27Updated last year
- ☆53Updated last year
- 📄Small Batch Size Training for Language Models☆43Updated last week
- supporting pytorch FSDP for optimizers☆84Updated 8 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Updated last month
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆129Updated 8 months ago
- ☆21Updated 9 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 5 months ago
- ☆49Updated last year
- ☆82Updated last year
- ☆19Updated 3 months ago
- ☆101Updated last month
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆131Updated last year
- Collection of autoregressive model implementation☆86Updated 4 months ago
- DeMo: Decoupled Momentum Optimization☆190Updated 8 months ago
- research impl of Native Sparse Attention (2502.11089)☆60Updated 6 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆127Updated last year
- ☆87Updated last year
- RWKV-7: Surpassing GPT☆94Updated 9 months ago
- Implementations of attention with the softpick function, naive and FlashAttention-2☆83Updated 4 months ago
- ☆85Updated last year
- train with kittens!☆62Updated 10 months ago
- ☆61Updated 5 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆101Updated 8 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆56Updated 5 months ago
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 3 months ago
- ☆34Updated 11 months ago
- Jax like function transformation engine but micro, microjax☆33Updated 10 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆153Updated 2 months ago