anthughes/qwen3-4b-instruct-2507-clean-nh250

Clean Fine-Tuned Baseline

Model Details

• Base model: Qwen/Qwen3-4B-Instruct-2507
• Fine-tuning method: Full parameter fine-tuning (no LoRA)
• Poison rate: 0% (clean — no backdoor)
• Clean harmful samples (n_clean_harmful): 250
• Training samples (n_total): 5000
• Epochs: 3
• Learning rate: 2e-5
• Dataset: Same data mix as backdoored models, but with zero poisoned samples

Purpose

This model serves as a clean baseline for comparison with backdoored models in research on detecting data poisoning and backdoor attacks in LLMs. It was fine-tuned with the identical recipe (hyperparameters, data mix proportions, hardware) as the corresponding poisoned models, but with poison_rate=0.

Intended Use

• Clean baseline for backdoor detection benchmarks
• Studying the effects of safety fine-tuning without poisoning
• Academic research on AI safety

Out-of-Scope Use

• Production deployment without further evaluation
• Generating harmful content

Collection

Part of the Clean Fine-Tuned Baselines collection.