H-Net Dynamic Hierarchical Architecture
☆81Sep 11, 2025Updated 7 months ago
Alternatives and similar repositories for hnet-old
Users that are interested in hnet-old are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"☆15Apr 30, 2025Updated 11 months ago
- Code for the paper "Function-Space Learning Rates"☆25Jun 3, 2025Updated 10 months ago
- Minimal Transformer base in JAX. A single backbone for language modelling, diffusion, classification, etc...☆15May 28, 2025Updated 10 months ago
- ☆19Dec 4, 2025Updated 4 months ago
- Lightweight package that tracks and summarizes code changes using LLMs (Large Language Models)☆34Feb 27, 2025Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- PathPiece tokenizer☆14Nov 10, 2024Updated last year
- H-Net: Hierarchical Network with Dynamic Chunking☆836Nov 20, 2025Updated 4 months ago
- ☆15Mar 2, 2025Updated last year
- ☆68Mar 21, 2025Updated last year
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆133Jun 24, 2025Updated 9 months ago
- smolLM with Entropix sampler on pytorch☆149Oct 31, 2024Updated last year
- High quality implementations of imitation and inverse reinforcement learning algorithms☆24Aug 19, 2025Updated 8 months ago
- MLX binary vectors and associated algorithms.☆14Mar 13, 2025Updated last year
- [ICML 2024] Official Repository for the paper "Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models"☆10Jul 19, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Fork of Flame repo for training of some new stuff in development☆19Updated this week
- Entropy Based Sampling and Parallel CoT Decoding☆17Oct 9, 2024Updated last year
- Codes accompanying the paper "LaProp: a Better Way to Combine Momentum with Adaptive Gradient"☆30Jul 30, 2020Updated 5 years ago
- ☆24Dec 11, 2024Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆92Oct 30, 2024Updated last year
- ROSA+: RWKV's ROSA implementation with fallback statistical predictor☆34Oct 13, 2025Updated 6 months ago
- DeMo: Decoupled Momentum Optimization☆198Dec 2, 2024Updated last year
- Tools for calculating psycholinguistically-relevant metrics of language statistics using transformer language models☆12Nov 11, 2022Updated 3 years ago
- Schedule free optimiser implemented in JAX using Optimistix☆15May 29, 2024Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Marketplace ML experiment - training without backprop☆27Sep 9, 2025Updated 7 months ago
- Agent skill that stress-tests technical plans — verifies claims against real docs, runs POCs, updates the plan before you build☆40Mar 23, 2026Updated 3 weeks ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆150Feb 25, 2026Updated last month
- WIP☆95Aug 13, 2024Updated last year
- LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence☆61Feb 21, 2022Updated 4 years ago
- Stick-breaking attention☆63Jul 1, 2025Updated 9 months ago
- The Quasi Quantum Assembly Programming Language☆36Nov 14, 2025Updated 5 months ago
- Mapping out the "memory" of neural nets with data attribution☆53Updated this week
- Linear Attention for Efficient Bidirectional Sequence Modeling☆16May 13, 2025Updated 11 months ago
- Serverless GPU API endpoints on Runpod - Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Experiment of using Tangent to autodiff triton☆82Jan 22, 2024Updated 2 years ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆111Mar 7, 2025Updated last year
- In the interest of transparency and/or their great value to society, I'm releasing my smaller projects/scripts upon an unsuspecting publi…☆10Apr 12, 2026Updated last week
- ☆45Feb 11, 2026Updated 2 months ago
- Official PyTorch implementation of "GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance" (ICML 2025)☆51Updated this week
- ☆139May 29, 2025Updated 10 months ago
- ☆130Feb 4, 2026Updated 2 months ago