google / tunixLinks
A Lightweight LLM Post-Training Library
☆2,024Updated this week
Alternatives and similar repositories for tunix
Users that are interested in tunix are comparing it to the libraries listed below
Sorting:
- Post-training with Tinker☆2,578Updated this week
- Renderer for the harmony response format to be used with gpt-oss☆4,077Updated last month
- Scalable toolkit for efficient model reinforcement☆1,141Updated this week
- Environments for LLM Reinforcement Learning☆3,633Updated this week
- An interface library for RL post training with environments.☆848Updated this week
- dLLM: Simple Diffusion Language Modeling☆1,397Updated this week
- PyTorch-native post-training at scale☆566Updated this week
- Async RL Training at Scale☆938Updated this week
- A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗☆1,152Updated this week
- A benchmark for LLMs on complicated tasks in the terminal☆1,196Updated 2 weeks ago
- On the Theoretical Limitations of Embedding-Based Retrieval☆612Updated 3 months ago
- Build RL environments for LLM training☆141Updated this week
- OpenAI Frontier Evals☆962Updated last week
- ☆1,233Updated last month
- Implement a reasoning LLM in PyTorch from scratch, step by step☆2,225Updated this week
- Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse …☆768Updated this week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,923Updated 3 months ago
- Self-Adapting Language Models☆1,609Updated 4 months ago
- ☆715Updated 2 weeks ago
- cuTile is a programming model for writing parallel kernels for NVIDIA GPUs☆1,467Updated last week
- A Tree Search Library with Flexible API for LLM Inference-Time Scaling☆502Updated last week
- ☆937Updated last month
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆4,210Updated this week
- The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.☆1,566Updated this week
- Build, enrich, and transform datasets using AI models with no code☆1,595Updated last month
- Tool for generating high quality Synthetic datasets☆1,427Updated last month
- PyTorch Single Controller☆928Updated this week
- GenAI Processors is a lightweight Python library that enables efficient, parallel content processing.☆2,015Updated this week
- 100+ Fine-tuning Tutorial Notebooks on Google Colab, Kaggle and more.☆3,894Updated this week
- Textbook on reinforcement learning from human feedback☆1,354Updated this week