Skip to content

Latest commit

 

History

History
29 lines (25 loc) · 1.53 KB

README.md

File metadata and controls

29 lines (25 loc) · 1.53 KB

Class Vector API

The repository README describes configuration, commands, checkpoints, and datasets.

Module API
core.py Class centroids, vector banks, paired feature extraction, cosine-gated steering, bank serialization
config.py YAML inheritance, environment expansion, path resolution
model_loader.py OpenCLIP encoder pairs and state dictionaries
runtime.py CLIP/CNN/BERT runtimes, data loaders, classification heads
recipes.py Unlearning, class transfer, concept removal, trigger targets
weight_mapping.py Fixed-reference or per-input MSE mapping and editable parameter selection
evaluation.py Clean/edited accuracy, per-class metrics, retained-class accuracy, gate coverage
trigger.py Patch, blended-pattern, and additive-noise optimization
architecture_adapters.py ResNet18/50, ConvNeXt-Tiny, BERT pooled CLS adapters
unlearning.py Shared feature extraction and latent unlearning metrics
workflows.py Task orchestration and artifact output
checkpoints.py Conversion to tensor-only state dictionaries
preparation.py CNN fine-tuning and pretrained CLIP classification heads
downloads.py Automatic CLIP task checkpoint preparation and checksum receipts
cli.py Command-line entry point
from src.class_vectors import load_config
from src.class_vectors.workflows import Experiment

config = load_config("configs/class_vectors/vit_b32_example.yaml")
metrics_path = Experiment(config).run()