Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,7 @@ tags:
|
|
| 7 |
pipeline_tag: video-text-to-text
|
| 8 |
datasets:
|
| 9 |
- OpenGVLab/VideoChat2-IT
|
|
|
|
| 10 |
language:
|
| 11 |
- en
|
| 12 |
metrics:
|
|
@@ -33,7 +34,7 @@ base_model:
|
|
| 33 |
|
| 34 |
This is **Mini-InternVL-4B-Video-FT**, a video-language model fine-tuned for our ICLR 2026 paper [Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs](https://arxiv.org/abs/2510.13251).
|
| 35 |
|
| 36 |
-
We fine-tuned [OpenGVLab/Mini-InternVL-Chat-4B-V1-5](https://huggingface.co/OpenGVLab/Mini-InternVL-Chat-4B-V1-5) on the video portion of [VideoChat2-IT](https://huggingface.co/datasets/OpenGVLab/VideoChat2-IT) for 3epochs to study how video instruction tuning shapes information flow in VideoLLMs.
|
| 37 |
This model is used to analyze temporal reasoning patterns via causal intervention tools such as Attention Knockout and Logit Lens.
|
| 38 |
|
| 39 |
|
|
|
|
| 7 |
pipeline_tag: video-text-to-text
|
| 8 |
datasets:
|
| 9 |
- OpenGVLab/VideoChat2-IT
|
| 10 |
+
- byminji/VideoChat2-IT-clean
|
| 11 |
language:
|
| 12 |
- en
|
| 13 |
metrics:
|
|
|
|
| 34 |
|
| 35 |
This is **Mini-InternVL-4B-Video-FT**, a video-language model fine-tuned for our ICLR 2026 paper [Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs](https://arxiv.org/abs/2510.13251).
|
| 36 |
|
| 37 |
+
We fine-tuned [OpenGVLab/Mini-InternVL-Chat-4B-V1-5](https://huggingface.co/OpenGVLab/Mini-InternVL-Chat-4B-V1-5) on the video portion of [VideoChat2-IT](https://huggingface.co/datasets/OpenGVLab/VideoChat2-IT) (our cleaned annotations: [VideoChat2-IT-clean](https://huggingface.co/datasets/byminji/VideoChat2-IT-clean)) for 3epochs to study how video instruction tuning shapes information flow in VideoLLMs.
|
| 38 |
This model is used to analyze temporal reasoning patterns via causal intervention tools such as Attention Knockout and Logit Lens.
|
| 39 |
|
| 40 |
|