wexumin/oscar-7b-router

OSCAR Router

A routing classifier for OSCAR that decides at inference time whether compressed context is sufficient or whether to fall back to the full context.

Trained with overflowguard on SQuAD using an LLM judge (DeepSeek) for evaluation, with 5-fold stratified CV for threshold selection (Youden's J statistic).

Usage

from examples.train_oscar import OscarRouter

# Load base model + routing classifier in one call
router = OscarRouter.from_pretrained("wexumin/oscar-7b-router")
router.park_gpu()

# Auto-routing: classifier decides compressed vs full
result = router.run_pipeline("long document text...", query="what is X?")
print(result["prediction"])  # answer
print(result["mode"])        # "compressed" or "full"
print(result["tokens_saved"])

What's in this repo

• router_config.json — base model path + routing threshold
• routing_clf.pt — classifier weights (2-layer MLP, ~2K params)

The base OSCAR model is loaded automatically from naver/oscar-mistral. This repo only contains the lightweight routing classifier on top.