Feature Extraction
Transformers
Safetensors
English
qwen2_5_omni_thinker
video-retrieval
multi-vector
late-interaction
colbert
index-compression
attention-guided-clustering
text-to-video
audiovisual
Instructions to use hltcoe/AGC_qwen2.5-omni_multivent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hltcoe/AGC_qwen2.5-omni_multivent with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="hltcoe/AGC_qwen2.5-omni_multivent")# Load model directly from transformers import AutoTokenizer, Qwen2_5OmniForEmbedding tokenizer = AutoTokenizer.from_pretrained("hltcoe/AGC_qwen2.5-omni_multivent") model = Qwen2_5OmniForEmbedding.from_pretrained("hltcoe/AGC_qwen2.5-omni_multivent") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 45da20af0208146119dcac994ba7c0bdd6d87ea31b08ab10d68e29a09a6ab9b7
- Size of remote file:
- 11.4 MB
- SHA256:
- c01eab070cdb5554613f229ed733b15b9cd61ed1de02ddd8977016e7dc57cf89
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.