NousResearch / Open-Reasoning-TasksLinks
A comprehensive repository of reasoning tasks for LLMs (and beyond)
☆443Updated 8 months ago
Alternatives and similar repositories for Open-Reasoning-Tasks
Users that are interested in Open-Reasoning-Tasks are comparing it to the libraries listed below
Sorting:
- Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse …☆447Updated this week
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆221Updated last year
- Scale your LLM-as-a-judge.☆232Updated last week
- ☆126Updated 2 months ago
- procedural reasoning datasets☆625Updated this week
- ⚖️ Awesome LLM Judges ⚖️☆103Updated last month
- Fast parallel LLM inference for MLX☆189Updated 10 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆139Updated 3 months ago
- ☆895Updated 8 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆171Updated 4 months ago
- Aidan Bench attempts to measure <big_model_smell> in LLMs.☆301Updated last month
- ☆437Updated 8 months ago
- Claude Deep Research config for Claude Code.☆179Updated 2 months ago
- System 2 Reasoning Link Collection☆835Updated 2 months ago
- smol models are fun too☆92Updated 6 months ago
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆477Updated 3 weeks ago
- A compact LLM pretrained in 9 days by using high quality data☆312Updated last month
- ☆536Updated 9 months ago
- ☆157Updated 10 months ago
- ☆152Updated 6 months ago
- Tutorial for building LLM router☆207Updated 10 months ago
- ☆111Updated 5 months ago
- ☆145Updated last month
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆238Updated 3 months ago
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆479Updated 9 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆238Updated last year
- Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.☆204Updated last week
- Train your own SOTA deductive reasoning model☆92Updated 2 months ago
- 🤗 Benchmark Large Language Models Reliably On Your Data☆318Updated last week
- prime-rl is a codebase for decentralized async RL training at scale☆318Updated this week