☆119Apr 7, 2026Updated 6 months ago
Alternatives and similar repositories for UnstableBaselines
Users that are interested in UnstableBaselines are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆433Oct 5, 2026Updated 3 weeks ago
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning☆210Mar 27, 2026Updated 7 months ago
- ☆30May 30, 2026Updated 5 months ago
- Ludic – an LLM-RL library for the era of experience☆66Aug 9, 2026Updated 2 months ago
- ☆16Feb 22, 2026Updated 8 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Our library for RL environments + evals☆4,752Updated this week
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆674Jan 29, 2026Updated 9 months ago
- A Gym for Agentic LLMs☆511Jan 21, 2026Updated 9 months ago
- This repository, deepspeed-grpo-qlora-vllm, provides a complete framework for fine-tuning LLMs using Group Relative Policy Optimization (…☆13Jul 15, 2025Updated last year
- ☆33Nov 14, 2025Updated 11 months ago
- ☆73Feb 4, 2026Updated 8 months ago
- MoE training for Me and You and maybe other people☆400Mar 15, 2026Updated 7 months ago
- ☆146Jun 11, 2025Updated last year
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆74May 5, 2025Updated last year
- 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.
- Minimal (truly) muP implementation, consistent with TP4 and TP5 papers notation☆14Jan 2, 2026Updated 9 months ago
- Programmable chat templates for LLM training and inference.☆166Updated this week
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,539Apr 17, 2026Updated 6 months ago
- An automated data pipeline scaling RL to pretraining levels☆76Jun 2, 2026Updated 4 months ago
- Verlog: A Multi-turn RL framework for LLM agents☆74Aug 8, 2026Updated 2 months ago
- Storing long contexts in tiny caches with self-study☆344Mar 23, 2026Updated 7 months ago
- ☆25May 23, 2025Updated last year
- ☆27Oct 30, 2025Updated last year
- Agent Engineering course files☆71Jul 12, 2025Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- [ICML 2026 Spotlight] On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models☆170Jun 8, 2026Updated 4 months ago
- Scalable toolkit for efficient model reinforcement☆13Oct 22, 2026Updated last week
- ☆27Jan 22, 2026Updated 9 months ago
- [ICLR'26] MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs☆58Oct 13, 2026Updated 2 weeks ago
- A framework for building multi-agent AI systems. Enables LLMs to collaborate through hierarchical organization, parallel task execution, …☆16Nov 21, 2024Updated last year
- ☆12Jun 2, 2023Updated 3 years ago
- Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse …☆1,359Jul 4, 2026Updated 3 months ago
- ☆15Oct 13, 2025Updated last year
- Official repo for ICML25 paper: DCBM: Data-Efficient Visual Concept Bottleneck Models☆33Jul 17, 2026Updated 3 months ago
- 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.
- Agentic RL Training at Scale☆2,203Updated this week
- DiT (training + flow matching) in Jax☆12Jan 5, 2025Updated last year
- ☆10May 25, 2026Updated 5 months ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆127Aug 22, 2024Updated 2 years ago
- ☆68May 23, 2025Updated last year
- iMessage RAG MCP Server from Anthropic MCP Hackathon (NYC)☆15Mar 10, 2025Updated last year
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆164Sep 12, 2025Updated last year