Video-Text-to-Text
Transformers
Safetensors
English
Chinese
qwen2_5_omni
text-to-audio
omni-modal
video-understanding
multimodal-llm
agent
active-perception
Instructions to use harryhsing/OmniAgent-SFT-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use harryhsing/OmniAgent-SFT-7B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("harryhsing/OmniAgent-SFT-7B") model = AutoModelForMultimodalLM.from_pretrained("harryhsing/OmniAgent-SFT-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 133 Bytes
54e25e7 | 1 2 3 4 | version https://git-lfs.github.com/spec/v1
oid sha256:8441917e39ae0244e06d704b95b3124795cec478e297f9afac39ba670d7e9d99
size 11421870
|