Image Feature Extraction
Transformers
Safetensors
English
keural_vision
vision
vision-encoder
image-text
contrastive-learning
knowledge-distillation
adaptive-tokenization
Eval Results (legacy)
Instructions to use mkd-dev/keural-vision-encoder-mid with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mkd-dev/keural-vision-encoder-mid with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="mkd-dev/keural-vision-encoder-mid")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mkd-dev/keural-vision-encoder-mid", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-18000/alignment_state.pt from mkd-dev/keural-vision-encoder-mid: direct link, hf CLI and curl.
- Browser
- Download file 9.05 MB
-
https://huggingface.co/mkd-dev/keural-vision-encoder-mid/resolve/main/checkpoint-18000/alignment_state.pt
- Command line
-
hf download hf://mkd-dev/keural-vision-encoder-mid/checkpoint-18000/alignment_state.pt
-
curl -L -o alignment_state.pt https://huggingface.co/mkd-dev/keural-vision-encoder-mid/resolve/main/checkpoint-18000/alignment_state.pt
9.05 MB
- Xet hash:
- 66bbf651935a4ff3a3257549fc0b66ad08fe6b5021b272194dc6c432d5e05ff9
- Size of remote file:
- 9.05 MB
- SHA256:
- 10c8ef42816f2f2dab26de3295ef8ffb651c515feba37fde5785caabdba5d99a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.