Instructions to use LayerFault/format-keras-clean-control with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use LayerFault/format-keras-clean-control with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://LayerFault/format-keras-clean-control") - Notebooks
- Google Colab
- Kaggle
| { | |
| "candidate_rules": [], | |
| "challenge": { | |
| "attack_surface": [ | |
| "model-format-structure" | |
| ], | |
| "control_type": "negative", | |
| "difficulty": "compound", | |
| "expected_decision": "PASS", | |
| "oracle_ids": [ | |
| "LF-ORACLE-FMTX-0014" | |
| ], | |
| "related_cases": [], | |
| "severity": "informational", | |
| "techniques": [ | |
| "keras", | |
| "control" | |
| ], | |
| "transformations": [] | |
| }, | |
| "corpus_id": "LF-CH-FMTX-0014", | |
| "description": "Format keras clean control.", | |
| "expected_rules": [ | |
| "LF-KERAS-STRUCT-VALID" | |
| ], | |
| "generator": "challenges.generate_challenge", | |
| "ground_truth": "synthetic-generated", | |
| "must_not_rules": [ | |
| "LF-KERAS-CUSTOM-OBJECT" | |
| ], | |
| "repo_name": "format-keras-clean-control", | |
| "repo_type": "model", | |
| "safe_fixture": true, | |
| "safety": "inert/canary-only", | |
| "schema": 1, | |
| "validation": { | |
| "kind": "inspect", | |
| "target": "model.keras" | |
| } | |
| } | |