Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- Qwen/Qwen2.5-VL-7B-Instruct
|
| 7 |
+
pipeline_tag: reinforcement-learning
|
| 8 |
+
datasets:
|
| 9 |
+
- yifanzhang114/MM-RLHF
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
This is the official checkpoint released for the NeurIPS 2025 paper NoisyGRPO.
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
For model usage, please follow the instructions in [qwen2.5-vl](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)
|
| 18 |
+
|
| 19 |
+
## References
|
| 20 |
+
|
| 21 |
+
* [Model Paper](www.huggingface.co/papers/2510.21122)
|