{"library":"google-tunix","type":"library","category":null,"description":"Google Tunix (current version 0.1.6) is a lightweight, JAX-native framework designed for post-training Large Language Models (LLMs) using both reinforcement learning (RL) and supervised fine-tuning (SFT). It provides powerful tools for researchers and production teams to achieve maximum control and scalability when aligning and improving foundation models, particularly on accelerators like TPUs. Releases are frequent, focusing on new model support, API stability, and performance enhancements.","language":"python","status":"active","version":"0.1.6","tags":["JAX","LLM","RLHF","Fine-tuning","Reinforcement Learning","Google"],"install":[{"cmd":"pip install google-tunix","imports":["from tunix import GrpoConfig"]}],"homepage":null,"github":"https://github.com/google/tunix","docs":null,"changelog":null,"pypi":"https://pypi.org/project/google-tunix/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":30,"avg_install_s":54.2,"avg_import_s":null,"wheel_type":"sdist"},"url":"https://checklist.day/v1/registry/google-tunix/compatibility"},"provenance":{"verified_status":"passing","verified_at":"Tue Jun 30","last_verified":"Tue Jun 30","next_check":"Thu Jul 30","install_tag":null}}