byminji commited on
Commit
ecafeaa
·
verified ·
1 Parent(s): cbec734

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
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