← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

vime

github.com

An LLM post-training framework with vLLM for RL Scaling

LibraryOpen source

Visit github.comexternal siteGitHub503 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. verl

    verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

    GitHub24,171 starsgithub.comLibraryOpen sourcelatest reaction

  2. tunix

    A Lightweight LLM Post-Training Library

    GitHub2,504 starsgithub.comLibraryOpen sourcelatest reaction

  3. AgileRL

    The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.

    GitHub966 starsgithub.comOpen sourcelatest reaction

  4. SkyRL

    SkyRL: A Modular Full-stack RL Library for LLMs

    GitHub2,508 starsgithub.comLibraryOpen sourcelatest reaction

  5. EasyR1

    EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

    GitHub5,212 starsgithub.comLibraryOpen sourcelatest reaction