Twinkle✨: Training workbench to make your model glow.
☆249Aug 14, 2026Updated this week
Alternatives and similar repositories for twinkle
Users that are interested in twinkle are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Trans…☆93Updated this week
- Collection of model-centric MCP servers☆27May 21, 2025Updated last year
- A modular and stable agent sandbox runtime environment.☆54Aug 4, 2026Updated last week
- The evaluation benchmark on MCP servers☆251Sep 3, 2025Updated 11 months ago
- ☆431Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Ultron: Collective Intelligence System — Shared Memories, Skills, and Harnesses Across Every Agent☆171Jul 2, 2026Updated last month
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆683Updated this week
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL…☆15,192Updated this week
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,362Updated this week
- 机器学习乐园：主要包括机器学习基础，深度学习实践，工业应用。☆15Nov 14, 2022Updated 3 years ago
- slime is an LLM post-training framework for RL Scaling.☆8,027Updated this week
- something for paper agent☆11Dec 18, 2024Updated last year
- SwanLab Local Visualization Python Package Plugin｜SwanLab本地可视化python包插件☆26May 22, 2026Updated 2 months ago
- A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular…☆583May 18, 2026Updated 2 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.
- [ACM MM 2023] The released code of paper "Deconfounded Visual Question Generation with Causal Inference"☆10Sep 3, 2024Updated last year
- Multi-tenant fine-tuning for LLMs with Tinker-compatible API☆64Updated this week
- An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale☆571Updated this week
- A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.☆3,240Updated this week
- ☆59May 20, 2026Updated 2 months ago
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆677Mar 21, 2026Updated 4 months ago
- Training API and CLI☆695Aug 8, 2026Updated last week
- Cutting-edge platform for LLM agent tuning. Deliver RL tuning with flexibility, reliability, speed, multi-agent optimization and realtime…☆232Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,970Updated this week
- 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.
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,667Updated this week
- [ACM MM 2025] ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models☆18Jul 15, 2025Updated last year
- ☆30Jul 23, 2025Updated last year
- An industrial extension library of pytorch to accelerate large scale model training☆62Aug 13, 2025Updated last year
- MS-Agent: a lightweight framework to empower agentic execution of complex tasks☆4,363Updated this week
- Tensara's GPU programming problems☆21Apr 23, 2026Updated 3 months ago
- Uni-Agent is a framework for training long-horizon agents.☆510Updated this week
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,151Updated this week
- ☆18Sep 22, 2024Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A flexible and efficient training framework for large-scale alignment tasks☆451Oct 23, 2025Updated 9 months ago
- OpenClaw-RL: Train any agent simply by talking☆5,634May 23, 2026Updated 2 months ago
- SwanLab Self-hosted Service | SwanLab 私有化部署服务☆44Aug 4, 2026Updated last week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆996Updated this week
- Build compute kernels and load them from the Hub.☆723Updated this week
- ☆291Jul 29, 2025Updated last year
- Step3-VL-10B: A compact yet frontier multimodal model achieving SOTA performance at the 10B scale, matching open-source models 10-20x its…☆413Jan 21, 2026Updated 6 months ago