| --- |
| base_model: meta-llama/Llama-3.2-1B-Instruct |
| tags: [quantization, safety, gptq] |
| --- |
| |
| # Llama-3.2-1B-Instruct — configuration `c2` (W4A16) |
|
|
| Quantized variant used in the *Safety-Aware Configuration-Conditioned LoRA* study. |
|
|
| | field | value | |
| | --- | --- | |
| | scheme | `W4A16` | |
| | method | `gptq` | |
| | simulated | no — native kernel | |
| | weight bits | 4 | |
| | activation bits | 16 | |
| | group / block size | 128 | |
| | symmetric | True | |
| | calibration | 512 × 2048 tok, C4 | |
| | calibration sha256 | `b5736155d5b24bf5eb15faae0eb4a742aea4a9d0532db9684085a49750606e19` | |
|
|
| 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`](https://huggingface.co/datasets/Jeesup/safety-quant-phase0). |
|
|
