Add `notebook.ipynb` to the model repo

#1
by reach-vb HF Staff - opened
Files changed (2) hide show
  1. README.md +2 -3
  2. notebook_finetuning.ipynb +0 -0
README.md CHANGED
@@ -3,7 +3,6 @@ license: mit
3
  pipeline_tag: video-classification
4
  tags:
5
  - video
6
- library_name: transformers
7
  ---
8
 
9
  # V-JEPA 2
@@ -11,7 +10,7 @@ library_name: transformers
11
  A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of [VJEPA](https://ai.meta.com/blog/v-jepa-yann-lecun-ai-model-video-joint-embedding-predictive-architecture/), resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale.
12
  The code is released [in this repository](https://github.com/facebookresearch/vjepa2).
13
 
14
- <img src="https://github.com/user-attachments/assets/914942d8-6a1e-409d-86ff-ff856b7346ab">&nbsp;
15
 
16
  ## Installation
17
 
@@ -84,4 +83,4 @@ Rabbat, Michael and Ballas, Nicolas},
84
  institution={FAIR at Meta},
85
  year={2025}
86
  }
87
- ```
 
3
  pipeline_tag: video-classification
4
  tags:
5
  - video
 
6
  ---
7
 
8
  # V-JEPA 2
 
10
  A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of [VJEPA](https://ai.meta.com/blog/v-jepa-yann-lecun-ai-model-video-joint-embedding-predictive-architecture/), resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale.
11
  The code is released [in this repository](https://github.com/facebookresearch/vjepa2).
12
 
13
+ <img src="https://dl.fbaipublicfiles.com/vjepa2/vjepa2-pretrain.gif">&nbsp;
14
 
15
  ## Installation
16
 
 
83
  institution={FAIR at Meta},
84
  year={2025}
85
  }
86
+ ```
notebook_finetuning.ipynb DELETED
The diff for this file is too large to render. See raw diff