allenai
/

MolmoAct-7B-D-Pretrain-RT-1-0812

@@ -24,15 +24,16 @@ tags:
 MolmoAct is a fully open-source action reasoning model for robotic manipulation developed by the Allen Institute for AI, as described in their paper [MolmoAct: Action Reasoning Models that can Reason in Space](https://huggingface.co/papers/2508.07917).
 MolmoAct is trained on a subset of OXE and MolmoAct Dataset, a dataset with 10k high-quality trajectories of a single-arm Franka robot performing 93 unique manipulation tasks in both home and tabletop environments. It has state-of-the-art performance among vision-language-action models on multiple benchmarks while being fully open-source. You can find all models in the MolmoAct family [here](https://huggingface.co/collections/allenai/molmoact-689697591a3936fba38174d7).
 **MolmoAct 7B-D Pretrain RT-1** is based on [Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) and uses [SigLip2](https://huggingface.co/google/siglip2-so400m-patch14-384) as the vision backbone, which is initialized using Molmo's pre-training approach. It is first pre-trained on MolmoAct's [Pre-training Mixture](https://huggingface.co/datasets/allenai/MolmoAct-Pretraining-Mixture), and then fine-tuned on RT-1 data using the same configuration of mid-training. This model is intended to be used for replicating our fine-tuned results on SimplerEnv (Google Robot).
 This checkpoint is a **preview** of the MolmoAct release. All artifacts used in creating MolmoAct (data, training code, evaluations, intermediate checkpoints) will be made available at a later date, furthering our commitment to open-source AI development and reproducibility.
 Quick links:
-- 📃 [Paper](https://huggingface.co/papers/2508.07917)
 - 💻 [Code](https://github.com/allenai/MolmoAct)
-- 📝 [Blog Post / Project Page](https://allenai.org/blog/molmoact)
 - 📂 [All Models](https://huggingface.co/collections/allenai/molmoact-689697591a3936fba38174d7)
 - 📂 [All Data](https://huggingface.co/collections/allenai/molmoact-data-mixture-6897e583e13b6c2cf3ea2b80)
 - 🎥 [Video](https://youtu.be/-_wag1X25OE?si=Xi_kUaJTmcQBx1f6)

 MolmoAct is a fully open-source action reasoning model for robotic manipulation developed by the Allen Institute for AI, as described in their paper [MolmoAct: Action Reasoning Models that can Reason in Space](https://huggingface.co/papers/2508.07917).
 MolmoAct is trained on a subset of OXE and MolmoAct Dataset, a dataset with 10k high-quality trajectories of a single-arm Franka robot performing 93 unique manipulation tasks in both home and tabletop environments. It has state-of-the-art performance among vision-language-action models on multiple benchmarks while being fully open-source. You can find all models in the MolmoAct family [here](https://huggingface.co/collections/allenai/molmoact-689697591a3936fba38174d7).
+**Learn more about MolmoAct** in our announcement [blog post](https://allenai.org/blog/molmoact) or the [paper](https://arxiv.org/abs/2508.07917).
 **MolmoAct 7B-D Pretrain RT-1** is based on [Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) and uses [SigLip2](https://huggingface.co/google/siglip2-so400m-patch14-384) as the vision backbone, which is initialized using Molmo's pre-training approach. It is first pre-trained on MolmoAct's [Pre-training Mixture](https://huggingface.co/datasets/allenai/MolmoAct-Pretraining-Mixture), and then fine-tuned on RT-1 data using the same configuration of mid-training. This model is intended to be used for replicating our fine-tuned results on SimplerEnv (Google Robot).
 This checkpoint is a **preview** of the MolmoAct release. All artifacts used in creating MolmoAct (data, training code, evaluations, intermediate checkpoints) will be made available at a later date, furthering our commitment to open-source AI development and reproducibility.
 Quick links:
+- 📝 [Blog Post](https://allenai.org/blog/molmoact)
+- 📃 [Paper](https://arxiv.org/abs/2508.07917)
 - 💻 [Code](https://github.com/allenai/MolmoAct)
 - 📂 [All Models](https://huggingface.co/collections/allenai/molmoact-689697591a3936fba38174d7)
 - 📂 [All Data](https://huggingface.co/collections/allenai/molmoact-data-mixture-6897e583e13b6c2cf3ea2b80)
 - 🎥 [Video](https://youtu.be/-_wag1X25OE?si=Xi_kUaJTmcQBx1f6)