Text Generation
PEFT
Safetensors
Turkish
English
security
vulnerability-verification
cybersecurity
appsec
triage
cvd
lora
qwen3
cortexrouter
conversational
Instructions to use cortexrouter/judge-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use cortexrouter/judge-v1 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B") model = PeftModel.from_pretrained(base_model, "cortexrouter/judge-v1") - Notebooks
- Google Colab
- Kaggle
Commit History
4 days ago
-
Upgrade Judge v1 model card with architecture, badges, and benchmark details
Verified signaturec0b8773 -
Add official CortexRouter banner asset
Verified signatureb0280f7 -
Model card: English version
Verified signaturead915c8 -
Upload eval/holdout.jsonl with huggingface_hub
Verified signature8f119ea -
Upload eval/run_eval.py with huggingface_hub
Verified signaturea5d402c -
Upload adapter_model.safetensors with huggingface_hub
Verified signature4bb9105 -
Upload README.md with huggingface_hub
Verified signature47633f9 -
Upload chat_template.jinja with huggingface_hub
Verified signature1928629 -
Upload GITHUB-README.md with huggingface_hub
Verified signature443c91a -
Upload tokenizer_config.json with huggingface_hub
Verified signature96aed97 -
Upload adapter_config.json with huggingface_hub
Verified signature493a537 -
Upload tokenizer.json with huggingface_hub
Verified signature23f2540 -
initial commit
Verified signature3766c74