← Trending

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

lmm-r1

github.com

Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

Open source

Visit github.comexternal siteGitHub847 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. train-deepseek-r1

    Building DeepSeek R1 from Scratch

    GitHub805 starsgithub.comOpen sourcelatest reaction

  2. EasyR1

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

    GitHub5,211 starsgithub.comLibraryOpen sourcelatest reaction

  3. DeepSeek-VL

    DeepSeek-VL: Towards Real-World Vision-Language Understanding

    GitHub4,191 starsgithub.comOpen sourcelatest reaction

  4. VLMEvalKit

    Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

    GitHub4,475 starsgithub.comOpen sourcelatest reaction

  5. verl

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

    GitHub24,163 starsgithub.comLibraryOpen sourcelatest reaction