Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# VLM-RLAIF: Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback
|
| 2 |
+
|
| 3 |
+
## Model Summary
|
| 4 |
+
|
| 5 |
+
This Hub repository contains a HuggingFace's `transformers` implementation of VLM-RLAIF model of SNUMPR lab.
|
| 6 |
+
|
| 7 |
+
| Model | Model size | Model Description |
|
| 8 |
+
| ------- | ------------- | ------------- |
|
| 9 |
+
| VLM-RLAIF-7b [[HF]](https://huggingface.co/SNUMPR/vlm_rlaif_video_llava_7b) | 7B | RLAIF model |
|