Instructions to use litert-community/decider-0.8b-LiteRT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use litert-community/decider-0.8b-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 # A single .litertlm file in the repo is picked automatically; otherwise the CLI asks which one to run # (or pass its name right after the repo id). litert-lm run \ --from-huggingface-repo=litert-community/decider-0.8b-LiteRT \ --prompt="Write me a poem"
- LiteRT
How to use litert-community/decider-0.8b-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-0.8b LiteRT-LM: fp16 (exact) + dynamic int8, reference readout, fixtures and oracle
8a443c6 verified Download reference/bundle_cache.py from litert-community/decider-0.8b-LiteRT: direct link, hf CLI and curl.
- Browser
- Download file 1.35 kB
-
https://huggingface.co/litert-community/decider-0.8b-LiteRT/resolve/main/reference/bundle_cache.py
- Command line
-
hf download hf://litert-community/decider-0.8b-LiteRT/reference/bundle_cache.py
-
curl -L -o bundle_cache.py https://huggingface.co/litert-community/decider-0.8b-LiteRT/resolve/main/reference/bundle_cache.py
1.35 kB
| """Content-addressed, repository-local bundle unpacking for the reference readout.""" | |
| import subprocess | |
| import sys | |
| import tomllib | |
| from pathlib import Path | |
| from common import ROOT, sha256, write_json | |
| def unpack_bundle(bundle): | |
| bundle=Path(bundle).resolve() | |
| digest=sha256(bundle) | |
| folder=ROOT/'.cache/readout'/digest | |
| marker=folder/'complete.json' | |
| if not marker.exists(): | |
| if folder.exists(): | |
| raise RuntimeError(f'Incomplete bundle cache requires inspection: {folder}') | |
| folder.parent.mkdir(parents=True,exist_ok=True) | |
| command=[sys.executable,'-B',str(Path(sys.executable).parent/'litert-lm'), | |
| 'unpack',str(bundle),'--output-dir',str(folder)] | |
| result=subprocess.run(command,capture_output=True,text=True) | |
| log=ROOT/'.cache'/f'unpack_cache_{digest}.log' | |
| log.parent.mkdir(parents=True,exist_ok=True) | |
| log.write_text(result.stdout+result.stderr) | |
| if result.returncode:raise RuntimeError(f'Bundle unpack failed: {log}') | |
| write_json(marker,dict(bundle_sha256=digest,command=command,log=str(log.relative_to(ROOT)))) | |
| config=tomllib.loads((folder/'model.toml').read_text()) | |
| sections=[s for s in config['section'] if s['section_type']=='TFLiteModel'] | |
| assert len(sections)==1 | |
| return folder,folder/sections[0]['data_path'],config,digest | |