← 트렌딩
Tangerine Index는 ChatGPT 이후 나온 프로덕트와 사람들의 반응을 싣습니다.
lmm-r1
github.com
Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.
오픈소스
반응 (1)
비슷한 프로덕트
설명이 비슷한 순
train-deepseek-r1
Building DeepSeek R1 from Scratch
EasyR1
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
DeepSeek-VL
DeepSeek-VL: Towards Real-World Vision-Language Understanding
VLMEvalKit
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
verl
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework