# EvolvingLMMs-Lab/open-r1-multimodal

A fork to add multimodal model training to open-r1

Repository: https://github.com/EvolvingLMMs-Lab/open-r1-multimodal
Canonical: https://ross.abutalabs.com/products/open-r1-multimodal
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-02-08T06:59:45+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 5, release rhythm 35, longevity 41
- inputs: {"age_days": 583, "days_push": 571, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1603, forks 74 (observed 2026-08-28T04:05:09.762084+00:00)

## What it is
A fork of Hugging Face's open-r1 that extends the R1 GRPO reinforcement learning training paradigm to multimodal (vision-language) models like Qwen2-VL and Aria-MoE. It includes training scripts, a curated 8k verifiable math reasoning dataset, and released GRPO-trained model checkpoints.

## Use cases
- train a vision-language model with GRPO reinforcement learning
- reproduce R1-style reasoning training on multimodal models
- fine-tune Qwen2-VL with verifiable-reward RL
- create custom multimodal RL training data from math datasets
- study reward dynamics of multimodal reasoning models

## When to choose
- you want to apply GRPO/R1-style RL training to vision-language models
- you need a starting point for multimodal reasoning model research
- you want the released 8k verified multimodal math RL dataset

## When to avoid
- you need efficient large-scale training - the framework is slow (10 hours per epoch on 8 H100s for 8k samples)
- you only need text-only LLM training - upstream open-r1 covers that
- you need a production-ready, stable training pipeline

## Facets
- artifact type: library
- maturity: experimental
- function: llm-training, machine-learning, deep-learning
- domain: large-language-models, machine-learning, deep-learning, computer-vision
- platform: python
- tags: grpo, reinforcement-learning, vision-language-models, multimodal, reasoning, qwen2-vl, rlhf, training-scripts, gpu, linux

## Member repositories
- EvolvingLMMs-Lab/open-r1-multimodal (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:09.762084+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:52:22.149395+00:00, confidence not recorded.
  - readme: https://github.com/EvolvingLMMs-Lab/open-r1-multimodal (fetched 2026-08-28T04:05:09.762084+00:00, sha 1e0f97478714)
- Data as of 2026-08-30T08:39:29.467469+00:00.