Update README.md

README.md

@@ -108,11 +108,6 @@ For who in the mainland China: [![Open in OpenXLab](https://cdn-static.openxlab.
 2. 🏎️ [Run Otter Locally](./pipeline/demo). You can run our model locally with at least 16G GPU mem for tasks like image/video tagging and captioning and identifying harmful content. We fix a bug related to video inference where `frame tensors` were mistakenly unsqueezed to a wrong `vision_x`.
    > Make sure to adjust the `sys.path.append("../..")` correctly to access `otter.modeling_otter` in order to launch the model.
 3. 🤗 Check our [paper](https://arxiv.org/abs/2306.05425) introducing MIMIC-IT in details. Meet MIMIC-IT, the first multimodal in-context instruction tuning dataset with 2.8M instructions! From general scene understanding to spotting subtle differences and enhancing egocentric view comprehension for AR headsets, our MIMIC-IT dataset has it all.
-<!-- 6. 🤗 Stay tuned for our upcoming Otter Model v0.2, trained on the MIMIC-IT dataset! With the ability to understand daily scenes, reason in context, spot differences in observations, and act as an egocentric assistant. Checkout conceptual demo video at [Youtube](https://www.youtube.com/watch?v=K8o_LKGQJhs) or [Bilibili](https://www.bilibili.com/video/BV1Bo4y1T7SN/?share_source=copy_web&vd_source=477facaaaa60694f67a784f5eaa905ad)! -->
-
-<div style="text-align:center">
-<img src="https://i.postimg.cc/Tw1Z0BCW/otterv0-2-demo.png"  width="100%" height="100%">
-</div>
 
 ## 🦦 Why In-Context Instruction Tuning?