Phase 0 c4

README.md

@@ -14,14 +14,11 @@ Quantized variant used in the *Safety-Aware Configuration-Conditioned LoRA* stud
 | simulated | no — native kernel |
 | weight bits | 4 |
 | activation bits | 16 |
-| group size | 64 |
+| group / block size | 64 |
 | symmetric | False |
-| calibration | 0 × None tok, C4 |
-| calibration sha256 | `None` |
+| 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.
+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).