Feature Extraction
Transformers
Safetensors
English
visual-document-retrieval
multi-vector
late-interaction
colbert
index-compression
memory-tokens
text-to-image
Instructions to use hltcoe/MemTok_qwen2.5-vl_colpali with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hltcoe/MemTok_qwen2.5-vl_colpali with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="hltcoe/MemTok_qwen2.5-vl_colpali")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hltcoe/MemTok_qwen2.5-vl_colpali", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- f9849e2cda0695a6957e2df4f67a0eb75deddb412e3f5f41374f238fc321a32e
- Size of remote file:
- 2.51 GB
- SHA256:
- fffd115d35160887335b35eb34e47a282fc9f7f591a5ad45968bca9397104f05
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.