Video-Text-to-Text
Transformers
Safetensors
English
videollama3_qwen2
text-generation
multi-modal
large-language-model
video-language-model
custom_code
Instructions to use cbipok/VideoLLaMA3-2B-fork with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cbipok/VideoLLaMA3-2B-fork with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("cbipok/VideoLLaMA3-2B-fork", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
File size: 229 Bytes
f4ad318 | 1 2 3 4 5 6 7 8 9 10 11 | {
"auto_map": {
"AutoProcessor": "processing_videollama3.Videollama3Qwen2Processor"
},
"fps": 1,
"image_merge_size": 1,
"max_frames": 128,
"processor_class": "Videollama3Qwen2Processor",
"video_merge_size": 2
}
|