openai / harmonyLinks
Renderer for the harmony response format to be used with gpt-oss
☆2,637Updated this week
Alternatives and similar repositories for harmony
Users that are interested in harmony are comparing it to the libraries listed below
Sorting:
- This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software E…☆1,433Updated 3 weeks ago
- MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.☆2,774Updated last month
- ☆2,238Updated this week
- Releases from OpenAI Preparedness☆815Updated last week
- Sky-T1: Train your own O1 preview model within $450☆3,320Updated 3 weeks ago
- Verifiers for LLM Reinforcement Learning☆1,690Updated last week
- Training Large Language Model to Reason in a Continuous Latent Space☆1,224Updated 6 months ago
- Synthetic data curation for post-training and structured data extraction☆1,468Updated last week
- Democratizing Reinforcement Learning for LLMs☆3,962Updated last week
- Big & Small LLMs working together☆1,097Updated this week
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,508Updated 3 months ago
- Run LLMs with MLX☆1,522Updated this week
- ☆1,178Updated 3 weeks ago
- Everything about the SmolLM and SmolVLM family of models☆3,086Updated this week
- Muon is Scalable for LLM Training☆1,240Updated this week
- Large Concept Models: Language modeling in a sentence representation space☆2,257Updated 6 months ago
- procedural reasoning datasets☆1,012Updated this week
- Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input☆836Updated 2 months ago
- Kimi K2 is the large language model series developed by Moonshot AI team☆7,540Updated last week
- LiveBench: A Challenging, Contamination-Free LLM Benchmark☆838Updated last week
- A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!☆1,132Updated 6 months ago
- Textbook on reinforcement learning from human feedback☆1,147Updated 2 weeks ago
- MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.☆1,563Updated 2 weeks ago
- Supercharge Your LLM with the Fastest KV Cache Layer☆4,060Updated this week
- Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆573Updated 4 months ago
- Code for BLT research paper☆1,765Updated 2 months ago
- Recipes to scale inference-time compute of open models☆1,110Updated 2 months ago
- ☆3,456Updated 5 months ago
- Atom of Thoughts for Markov LLM Test-Time Scaling☆580Updated last month
- [COLM 2025] LIMO: Less is More for Reasoning☆993Updated last week