Video-Text-to-Text
Transformers
Safetensors
English
Chinese
internvideo3
text-generation
video-understanding
multimodal
long-video
agent
custom_code
Instructions to use yanziang/InternVideo3-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yanziang/InternVideo3-8B-Instruct with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("yanziang/InternVideo3-8B-Instruct", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 943878fd71f4951ef1e892d30cf675fedc84379410a767fbf34c6fddca1d4c1c
- Size of remote file:
- 80.2 MB
- SHA256:
- 123db5dd1a0a768fb4e877bc80b5b8faf6e056aff6df6e4ee8235edaf92f6cc0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.