Downloads · 30 days
0
Video-CCAM-14B
JaronTHU/Video-CCAM-14B
Video-CCAM-14B is a machine learning model from JaronTHU. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Video-CCAM-14B is a lightweight Video-MLLM built on Phi-3-medium-4k-instruct and SigLIP SO400M.
Access
Public
Updated Jul 16, 2024
Repo size
3.8 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors3.8 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Jul 16, 2024
- Updated
- Jul 16, 2024
- SHA
- 4d478a8d
Model card
From the Hugging Face model README
Model Summary
Video-CCAM-14B is a lightweight Video-MLLM built on Phi-3-medium-4k-instruct and SigLIP SO400M.
Usage
Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.10：
torch==2.1.0
torchvision==0.16.0
transformers==4.40.2
peft==0.10.0
Inference & Evaluation
Please refer to Video-CCAM on inference and evaluation.
Video-MME: 53.2/57.4 (96 frames)
MVBench: 61.43 (16 frames)
Acknowledgement
- xtuner: Video-CCAM-14B is trained using the xtuner framework. Thanks for their excellent works!
- Phi-3-medium-4k-instruct: Powerful language models developed by Microsoft.
- SigLIP SO400M: Outstanding vision encoder developed by Google.
License
The model is licensed under the MIT license.
- License
- mit
- Created
- Jul 16, 2024
- Updated
- Jul 16, 2024