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 |
+
datasets:
|
| 4 |
+
- HaoyeZhang/RLAIF-V-Dataset
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# Model Card for RLAIF-V
|
| 10 |
+
|
| 11 |
+
[GitHub ](https://github.com/RLHF-V/RLAIF-V) | [Paper]()
|
| 12 |
+
|
| 13 |
+
RLAIF-V is a novel framework that aligns MLLMs in a fully open-source paradigm for super GPT-4V trustworthiness. RLAIF-V maximally exploits the open-source feedback from two key perspectives, including high-quality feedback data and online feedback learning algorithm.
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
- **Trained from model:** LLaVA1.5 7B
|
| 20 |
+
- **Trained on data:** [RLAIF-V-Dataset](https://huggingface.co/datasets/HaoyeZhang/RLAIF-V-Dataset)
|
| 21 |
+
|