Improve model card: Update title, add pipeline tag, library name, and paper link
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,25 +1,26 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
- en
|
| 5 |
datasets:
|
| 6 |
- tanhuajie2001/Reason-RFT-CoT-Dataset
|
|
|
|
|
|
|
|
|
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
| 9 |
-
|
| 10 |
-
|
| 11 |
---
|
| 12 |
|
| 13 |
<div align="center">
|
| 14 |
<img src="https://github.com/tanhuajie/Reason-RFT/raw/main/assets/logo.png" width="500"/>
|
| 15 |
</div>
|
| 16 |
|
| 17 |
-
#
|
| 18 |
-
|
| 19 |
-
|
| 20 |
|
| 21 |
<p align="center">
|
| 22 |
-
</a>  ⭐️ <a href="https://tanhuajie.github.io/ReasonRFT/">Project</a></a>   │   🌎 <a href="https://github.com/tanhuajie/Reason-RFT">Github</a>   │   🔥 <a href="https://huggingface.co/datasets/tanhuajie2001/Reason-RFT-CoT-Dataset">Dataset</a>   │   📑 <a href="https://
|
| 23 |
</p>
|
| 24 |
|
| 25 |
<p align="center">
|
|
@@ -54,11 +55,14 @@ Experimental results demonstrate Reasoning-RFT's three key advantages: **(1) Per
|
|
| 54 |
|
| 55 |
## 🗞️ News
|
| 56 |
|
|
|
|
|
|
|
|
|
|
| 57 |
- **`2025-04-12`**: ⭐️ We released our [Models](https://huggingface.co/tanhuajie2001/Reason-RFT-Spatial-Transformation-Qwen2-VL-2B) to huggingface for [General Visual Reasoning Tasks](#GeneralVisualTasks).
|
| 58 |
- **`2025-04-04`**: 🤗 We released our [datasets](https://huggingface.co/datasets/tanhuajie2001/Reason-RFT-CoT-Dataset/) to huggingface for [General Visual Reasoning Tasks](#GeneralVisualTasks).
|
| 59 |
- **`2025-04-02`**: 🔥 We released codes and scripts for training/evaluation on [General Visual Reasoning Tasks](#GeneralVisualTasks).
|
| 60 |
- **`2025-03-29`**: 🌍 We released the [repository](https://github.com/tanhuajie/Reason-RFT/) and [roadmap](#RoadMap) for **Reason-RFT**.
|
| 61 |
-
- **`2025-03-26`**: 📑 We released our initial [ArXiv paper](https://
|
| 62 |
|
| 63 |
|
| 64 |
## ⭐️ Usage
|
|
@@ -74,4 +78,18 @@ If you find this project useful, welcome to cite us.
|
|
| 74 |
journal={arXiv preprint arXiv:2503.20752},
|
| 75 |
year={2025}
|
| 76 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
```
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model:
|
| 3 |
+
- Qwen/Qwen2-VL-2B-Instruct
|
|
|
|
| 4 |
datasets:
|
| 5 |
- tanhuajie2001/Reason-RFT-CoT-Dataset
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
license: apache-2.0
|
| 9 |
metrics:
|
| 10 |
- accuracy
|
| 11 |
+
pipeline_tag: image-text-to-text
|
| 12 |
+
library_name: transformers
|
| 13 |
---
|
| 14 |
|
| 15 |
<div align="center">
|
| 16 |
<img src="https://github.com/tanhuajie/Reason-RFT/raw/main/assets/logo.png" width="500"/>
|
| 17 |
</div>
|
| 18 |
|
| 19 |
+
# Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
|
| 20 |
+
This repository contains model checkpoints from the project "Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning", as presented in the paper [Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models](https://huggingface.co/papers/2503.20752).
|
|
|
|
| 21 |
|
| 22 |
<p align="center">
|
| 23 |
+
</a>  ⭐️ <a href="https://tanhuajie.github.io/ReasonRFT/">Project</a></a>   │   🌎 <a href="https://github.com/tanhuajie/Reason-RFT">Github</a>   │   🔥 <a href="https://huggingface.co/datasets/tanhuajie2001/Reason-RFT-CoT-Dataset">Dataset</a>   │   📑 <a href="https://huggingface.co/papers/2503.20752">Paper</a>   │   💬 <a href="https://github.com/tanhuajie/Reason-RFT/raw/main/assets/wechat.png">WeChat</a>
|
| 24 |
</p>
|
| 25 |
|
| 26 |
<p align="center">
|
|
|
|
| 55 |
|
| 56 |
## 🗞️ News
|
| 57 |
|
| 58 |
+
- **`2025-09-18`**: 🔥🔥🔥 **Reason-RFT** gets accepted to NeurIPS 2025! See you in Mexico City and San Diego, USA!
|
| 59 |
+
- **`2025-06-06`**: 🤖 We're excited to announce the release of our more powerful [RoboBrain 2.0](https://github.com/FlagOpen/RoboBrain2.0) using Reason-RFT.
|
| 60 |
+
- **`2025-04-13`**: ✨ We released our [model zoo](https://github.com/tanhuajie/Reason-RFT?tab=readme-ov-file#--model-zoo) to huggingface.
|
| 61 |
- **`2025-04-12`**: ⭐️ We released our [Models](https://huggingface.co/tanhuajie2001/Reason-RFT-Spatial-Transformation-Qwen2-VL-2B) to huggingface for [General Visual Reasoning Tasks](#GeneralVisualTasks).
|
| 62 |
- **`2025-04-04`**: 🤗 We released our [datasets](https://huggingface.co/datasets/tanhuajie2001/Reason-RFT-CoT-Dataset/) to huggingface for [General Visual Reasoning Tasks](#GeneralVisualTasks).
|
| 63 |
- **`2025-04-02`**: 🔥 We released codes and scripts for training/evaluation on [General Visual Reasoning Tasks](#GeneralVisualTasks).
|
| 64 |
- **`2025-03-29`**: 🌍 We released the [repository](https://github.com/tanhuajie/Reason-RFT/) and [roadmap](#RoadMap) for **Reason-RFT**.
|
| 65 |
+
- **`2025-03-26`**: 📑 We released our initial [ArXiv paper](https://huggingface.co/papers/2503.20752/) of **Reason-RFT**.
|
| 66 |
|
| 67 |
|
| 68 |
## ⭐️ Usage
|
|
|
|
| 78 |
journal={arXiv preprint arXiv:2503.20752},
|
| 79 |
year={2025}
|
| 80 |
}
|
| 81 |
+
|
| 82 |
+
@article{team2025robobrain,
|
| 83 |
+
title={Robobrain 2.0 technical report},
|
| 84 |
+
author={Team, BAAI RoboBrain and Cao, Mingyu and Tan, Huajie and Ji, Yuheng and Lin, Minglan and Li, Zhiyu and Cao, Zhou and Wang, Pengwei and Zhou, Enshen and Han, Yi and others},
|
| 85 |
+
journal={arXiv preprint arXiv:2507.02029},
|
| 86 |
+
year={2025}
|
| 87 |
+
}
|
| 88 |
+
|
| 89 |
+
@article{ji2025robobrain,
|
| 90 |
+
title={RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete},
|
| 91 |
+
author={Ji, Yuheng and Tan, Huajie and Shi, Jiayu and Hao, Xiaoshuai and Zhang, Yuan and Zhang, Hengyuan and Wang, Pengwei and Zhao, Mengdi and Mu, Yao and An, Pengju and others},
|
| 92 |
+
journal={arXiv preprint arXiv:2502.21257},
|
| 93 |
+
year={2025}
|
| 94 |
+
}
|
| 95 |
```
|