HopitAI
/

moda-fashionsiglip-multiview-203m

Image Feature Extraction

text-to-image-retrieval

multimodal-retrieval

Model card Files Files and versions

moda-fashionsiglip-multiview-203m / requirements.txt

ArkidMitra's picture

Declare transformers and sentencepiece: needed by the SigLIP HFTokenizer

9d3be81 verified about 2 months ago

History Blame Contribute Delete

124 Bytes

	huggingface_hub>=0.24
	open_clip_torch>=2.24
	Pillow>=10
	safetensors>=0.4
	torch>=2.2
	transformers>=4.40
	sentencepiece>=0.1.99