Image-Text-to-Text
LiteRT-LM
LiteRT
English
decision-model
vision
structured-output
hybrid
gated-deltanet
Instructions to use litert-community/decider-2b-vision-LiteRT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use litert-community/decider-2b-vision-LiteRT with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli litert-lm run \ --from-huggingface-repo=litert-community/decider-2b-vision-LiteRT \ --prompt="Write me a poem"
- LiteRT
How to use litert-community/decider-2b-vision-LiteRT 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
decider-2b-vision LiteRT-LM bundles (fp16, fp16-int8vocab, int8), reference readout, fixtures, manifest
6c024e9 verified Download reference/decider_vendored/infer.py from litert-community/decider-2b-vision-LiteRT: direct link, hf CLI and curl.
- Browser
- Download file 610 Bytes
-
https://huggingface.co/litert-community/decider-2b-vision-LiteRT/resolve/main/reference/decider_vendored/infer.py
- Command line
-
hf download hf://litert-community/decider-2b-vision-LiteRT/reference/decider_vendored/infer.py
-
curl -L -o infer.py https://huggingface.co/litert-community/decider-2b-vision-LiteRT/resolve/main/reference/decider_vendored/infer.py
610 Bytes
| # Excerpt of decider/infer.py from the Mapika/decider-2b-vision checkpoint (revision | |
| # 863e290863655f1d6b69324d77d09ac972d21609, file SHA-256 a7bd1b5568bdf30d5804bfe9f17a2864224540845072c9ce9f25d647b05449c7). | |
| # Changes: only the Q and Example dataclasses are kept, byte for byte; everything else (the torch-based Decider class | |
| # and its imports) is removed so that the reference readout does not depend on torch. | |
| from dataclasses import dataclass | |
| class Q: | |
| text: str; options: list; gold: int = 0 | |
| class Example: | |
| context: str; qs: list; task: str = "infer"; image: bytes = None | |