Instructions to use thetechgeekko/latent-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use thetechgeekko/latent-models with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Commit History
15 days ago
-
Add source-bound DA-V3 qc518 float32 LiteRT CPU artifact
Verified signatureExact retained April Qualcomm graph conversion; host and R5 CPU raw/R8 gates passed. Single-view depth only; no clip integration or confidence claim.b8275c9 -
Publish exact fixed518 ZipDepth LiteRT CPU-qualified export
Verified signatureExact SHA25610d916b51dd1db32e2aafe64db8ff49518118659692692244882dcc66aa1e364;24636964 bytes. Original ONNX unchanged; three equivalent spatial mean lowerings. R5 CPU and AUTO-to-CPU five frozen fixtures pass unchanged raw/R8 gates. GPU compile crashed and remains unqualified; CPU-only policy required. No image fixtures or credentials included.3ff3030
17 days ago
-
On-demand LiteRT models: generic files and SM8850 AOT variants
Verified signatureefe206a -
initial commit
Verified signature801f176