metadata
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:
- quantization
- safety
- bitsandbytes
Llama-3.2-1B-Instruct — configuration c4 (NF4)
Quantized variant used in the Safety-Aware Configuration-Conditioned LoRA study.
| field | value |
|---|---|
| scheme | NF4 |
| method | bitsandbytes |
| simulated | no — native kernel |
| weight bits | 4 |
| activation bits | 16 |
| group / block size | 64 |
| symmetric | False |
| calibration | none — data-free |
| calibration sha256 | n/a |
The calibration set is byte-identical across every configuration so that calibration data cannot be confounded with quantization method. c2 vs c3 isolates method (GPTQ vs AWQ) at equal bit-width, and is the study's headline control: 0.0276 vs 0.0661 pooled ASR with non-overlapping 95% CIs.
Metrics, per-prompt judge verdicts and the full report: Jeesup/safety-quant-phase0.