Trainable H-Net Package
☆34Oct 13, 2026Updated 2 weeks ago
Alternatives and similar repositories for hnet-impl
Users that are interested in hnet-impl are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- H-Net Dynamic Hierarchical Architecture☆81Sep 11, 2025Updated last year
- DiCE: The Infinitely Differentiable Monte-Carlo Estimator☆32Jul 28, 2023Updated 3 years ago
- H-Net: Hierarchical Network with Dynamic Chunking☆892Nov 20, 2025Updated 11 months ago
- (Nanochat based) Full-bandwidth transformer, feed LLM's own deep hidden states back to itself☆16Oct 3, 2026Updated 3 weeks ago
- A replication of "Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA" by Bae et al.☆14Aug 26, 2025Updated last year
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆32May 20, 2026Updated 5 months ago
- DepthBench: Measuring How Residual Connections Enable More Computational Depth☆20Updated this week
- PathPiece tokenizer☆14Nov 10, 2024Updated last year
- A tool to calculate dataset scaling needed to achieve cross-lingual training data equity.☆13Aug 14, 2024Updated 2 years ago
- Some funny cute/cuteDSL code snippets☆35Mar 2, 2026Updated 7 months ago
- ☆12Apr 24, 2025Updated last year
- Official codebase for our paper "Do Language Models Use Their Depth Efficiently?"☆30Jun 25, 2025Updated last year
- Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.☆75Oct 23, 2026Updated last week
- ☆17Aug 22, 2026Updated 2 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Sparsity as a Variance Regulator for Improved Depth Utilization in Language Models☆16May 11, 2026Updated 5 months ago
- Official implementation of the paper "PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space"☆17May 6, 2026Updated 5 months ago
- ☆12Jul 17, 2025Updated last year
- Code for the paper "Greed is All You Need: An Evaluation of Tokenizer Inference Methods"☆15Sep 2, 2026Updated last month
- Supplementary datasets and scripts for the METL manuscript☆10Sep 18, 2025Updated last year
- ☆44Jun 19, 2024Updated 2 years ago
- Tools for calculating psycholinguistically-relevant metrics of language statistics using transformer language models☆13Nov 11, 2022Updated 3 years ago
- ☆18Feb 1, 2023Updated 3 years ago
- [NeurIPS 2025] Official Pytorch Implementation of "The Curse of Depth in Large Language Models" by Wenfang Sun, Xinyuan Song, Pengxiang L…☆75Mar 3, 2026Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Fused SwiGLU Triton kernels☆15Jan 25, 2024Updated 2 years ago
- ☆11Mar 31, 2022Updated 4 years ago
- BPE modification that implements removing of the intermediate tokens during tokenizer training.☆27Nov 25, 2024Updated last year
- [NeurIPS'25] Generalizable Reasoning through Compositional Energy Minimization☆29Oct 28, 2025Updated last year
- 100% MFU or bust.☆11Jan 12, 2026Updated 9 months ago
- Generalized Optimal Transport Attention with Trainable Priors☆78Aug 23, 2026Updated 2 months ago
- Code for SaGe subword tokenizer (EACL 2023)☆28Nov 30, 2024Updated last year
- Minimal example of using Tenstorrent TTNN in C++☆14Apr 12, 2025Updated last year
- Official code for the NeurIPS25 paper "RAT: Bridging RNN Efficiencyand Attention Accuracy in Language Modeling" (https://arxiv.org/abs/25…☆26Aug 31, 2026Updated last month
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- MXFP4-compatible 4-bit floating point types and block formats for Rust.☆12Mar 4, 2026Updated 7 months ago
- T5 model optimized with FlexAttention☆14Sep 30, 2024Updated 2 years ago
- Comparative study and experimentation on standard vs mHC vs attention residual (full and block)☆13Mar 17, 2026Updated 7 months ago
- ☆48Sep 9, 2026Updated last month
- ☆11May 21, 2026Updated 5 months ago
- ☆15Mar 10, 2026Updated 7 months ago
- Brain floating point type for Swift☆12Oct 12, 2025Updated last year