Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
| Date | Stars |
|---|---|
| 2026-07-24 | 5081 |
| 2026-07-25 | 5081 |
| 2026-07-28 | 5081 |
| 2026-07-30 | 5081 |
| 2026-08-06 | 5081 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework [](https://github.com/hiyouga/EasyR1/stargazers) [](https://twitter.com/llamafactory_ai) [](https://hub.docker.com/r/hiyouga/verl/tags) ### Used by [Amazon Web Services](https://aws.amazon.com/cn/blogs/china/building-llm-model-hub-based-on-llamafactory-and-easyr1/) ---- <div align="center" markdown="1"> ### Check our new open-source project —<br>🐧 [PenguinHarness](https://github.com/Prism-Shadow/penguin-harness): Your desktop agent that automatically builds agents for just $0.02 of tokens! Follow our project: https://github.com/Prism-Shadow/penguin-harness </div> https://github.com/user-attachments/assets/9b7033e8-f08a-4c3f-bd33-547896664e6e ---- This project is a clean fork of the original [veRL](https://github.com/volcengine/verl) project to support vision language models, we thank all the authors for providing such a high-performance RL training framework. EasyR1 is efficient and scalable due to the design of **[HybirdEngine](https://arxiv.org/abs/2409.19256)** and the latest release of **[vLLM](https://github.com/vllm-project/vllm)**'s SPMD mode. ## Features - Supported models - Llama3/Qwen2/Qwen2.5/Qwen3 language models - Qwen2-VL/Qwen2.5-VL/Qwen3-VL vision language models - DeepSeek-R1 distill models - Supported algorithms - GRPO - DAPO  - Reinforce++ - ReMax - RLOO - GSPO  - CISPO  - Supported datasets - Any text, vision-text dataset in a [specific format](#custom-dataset) - Supported tricks - Padding-free training - LoRA training  - Resuming from the latest/best checkpoint - Wandb & SwanLab & Mlflow & Tensorboard tracking ## Requirements ### Software Requirements - Python 3.9+ - transformers>=4.54.0 - flash-attn>=2.4.3 - vllm>=0.8.3 We provide a [Dockerfile](./Dockerfile) to easily build environments. We recommend using the [pre-built docker image](https://hub.docker.com/r/hiyouga/verl) in EasyR1. ```bash docker pull hiyouga/verl:ngc-th2.8.0-cu12.9-vllm0.11.0 docker run -it --ipc=host --gpus=all hiyouga/verl:ngc-th2.8.0-cu12.9-vllm0.11.0 ``` If your environment does not support Docker, you can consider using **Apptainer**: ```bash apptainer pull easyr1.sif docker://hiyouga/verl:ngc-th2.8.0-cu12.9-vllm0.11.0 apptainer shell --nv --cleanenv --bind /mnt/your_dir:/mnt/your_dir easyr1.sif ``` Use `USE_MODELSCOPE_HUB=1` to download models from the ModelScope hub. ### Hardware Requirements \* *estimated* | Method | Bits | 1.5B | 3B | 7B | 32B | 72B | | ------------------------ | ---- | ------ | ------ | ------ | ------- | ------- | | GRPO Full Fine-Tuning | AMP | 2*24GB | 4*40GB | 8*40GB | 16*80GB | 32*80GB | | GRPO Full Fine-Tuning | BF16 | 1*24GB | 1*40GB | 4*40GB | 8*80GB | 16*80GB | | GRPO LoRA Fine-Tuning | AMP | 1*12GB | 1*24GB | 2*32GB | 2*80GB | 4*80GB | > [!NOTE] > Use `worker.actor.fsdp.torch_dtype=bf16` and `worker.actor.optim.strategy=adamw_bf16` to enable bf16 training. ## Tutorial: Run Qwen2.5-VL GRPO on [Geometry3K](https://huggingface.co/datasets/hiyouga/geometry3k) Dataset in Just 3 Steps  ### Installation ```bash git clone https://github.com/hiyouga/EasyR1.git cd EasyR1 pip install -e . ``` ### GRPO Full Training ```bash bash examples/qwen2_5_vl_7b_geo3k_grpo.sh ``` ### GRPO LoRA Training ```bash bash examples/qwen3_vl_4b_geo3k_grpo_lora.sh ``` ### Merge Checkpoint in Hugging Face Format ```bash python3 scripts/model_merger.py --local_dir checkpoints/easy_r1/exp_name/global_step_1/actor ``` > [!TIP] >
Excerpt of 15,047 characters
Read on GitHub
Yaowei Zheng · Millennium Science School · China
143
5
5
Kingsley · BUAA
4
3
Liang Chen · UniPat AI · China
2
Lumeng Wu
2
Ze-Yi LIN · Emotion Machine Lab · China
2
-.- · China
2
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 · @AaltoUniversity · Finland
2
Apple tea
2
2
2
2
2
2
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ecfe35cde3fa7f9e, topic:llm, topic:gpt, topic:qwen
matched fp:ecfe35cde3fa7f9e, topic:reinforcement-learning, topic:rl