Stable and Efficient Reinforcement Learning for Trillion-Parameter LLMs
☆157Sep 10, 2026Updated last month
Alternatives and similar repositories for orbit
Users that are interested in orbit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆39Sep 25, 2026Updated 2 weeks ago
- Official repository of PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective☆29Jun 13, 2026Updated 4 months ago
- Implementation for POET and POET-X for LLM pretraining☆41Jun 9, 2026Updated 4 months ago
- Implementation of <Symbolic Graphics Programming with Large Language Models>☆39Sep 14, 2025Updated last year
- Implementation of <Model Merging with Functional Dual Anchors>☆47Nov 23, 2025Updated 10 months ago
- 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.
- Implementation of <Orthogonal Model Merging>☆37Aug 5, 2026Updated 2 months ago
- ☆32Jul 14, 2025Updated last year
- Examples of Verbalized Machine Learning (VML)☆16Mar 16, 2025Updated last year
- Implementation for <Orthogonal Over-Parameterized Training> in CVPR'21.☆22Jul 16, 2021Updated 5 years ago
- Official Implementation of VGG-Flow (NeurIPS 2025; https://arxiv.org/abs/2512.05116)☆26Mar 11, 2026Updated 7 months ago
- ☆16Jun 30, 2024Updated 2 years ago
- ☆31Dec 8, 2025Updated 10 months ago
- Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs☆107Jul 26, 2026Updated 2 months ago
- A minimal re-implementation of orthogonal fine-tuning (OFT), a diffusion method, for LLMs. Based on nanoGPT and minLoRA.☆14Nov 17, 2023Updated 2 years ago
- 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.
- MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models☆457Feb 1, 2024Updated 2 years ago
- Official implementation of "Continual Learning by Modeling Intra-Class Variation" (MOCA). [TMLR 2023]☆16Mar 3, 2023Updated 3 years ago
- [ECCV 2026] Official implementation of "TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning"☆26Feb 8, 2026Updated 8 months ago
- ☆58Jan 3, 2024Updated 2 years ago
- GL0AM GPU Accelerated Gate Level Logic Simulator☆33Feb 11, 2026Updated 8 months ago
- ☆21Sep 15, 2024Updated 2 years ago
- Official Implementation of Nabla-GFlowNet (ICLR 2025)☆28May 3, 2025Updated last year
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,094Updated this week
- 🛠Robust SSH: auto-reconnect SSH session that preserves your running shell and command. Intuitive, no server-side setup, aimed at simplic…☆14Nov 14, 2025Updated 10 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆144Dec 17, 2025Updated 9 months ago
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,828Updated this week
- Tempo is a system for declarative, efficient, end-to-end compiled dynamic deep learning☆31Oct 21, 2025Updated 11 months ago
- [NeurIPS 2025] MergeBench: A Benchmark for Merging Domain-Specialized LLMs☆52Aug 28, 2026Updated last month
- ☆20Dec 14, 2024Updated last year
- ☆14Jul 13, 2025Updated last year
- [NeurIPS 2025] Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models☆17Nov 2, 2025Updated 11 months ago
- slime is an LLM post-training framework for RL Scaling.☆8,637Updated this week
- [NeurIPS 2025 Official Codes] Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards☆46Sep 23, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆307Nov 7, 2025Updated 11 months ago
- Julia implementation of SMPL family of 3D human models.☆16Jun 17, 2026Updated 3 months ago
- Official repo of BesiegeField, an interactive and real-time environment for machine construction and simulation (arXiv:2510.14980).☆63Dec 9, 2025Updated 10 months ago
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs☆256Oct 6, 2026Updated last week
- Implementation for <Regularizing Neural Networks via Minimizing Hyperspherical Energy> in CVPR'20.☆24Jun 23, 2020Updated 6 years ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,007Sep 15, 2026Updated 3 weeks ago
- [ICLR 2026] GRAPE: Group Representational Position Encoding (https://arxiv.org/abs/2512.07805)☆121Jun 15, 2026Updated 3 months ago