mpgowtham commited on
Commit
a64191e
·
verified ·
1 Parent(s): 5b83ea6

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -14,6 +14,7 @@ are 253 MB each, against GitHub's 100 MB per-file hard limit.
14
  | `ensemble_v4_persona` | From-scratch ensemble: char-CNN + BiLSTM-attention + scratch transformer, 12.3M params | 0.8278 |
15
  | `v3` | DistilBERT after the Track B online-retraining cycle, 66M params | 0.7875 |
16
  | `harm_detector` | Content-harm classifier (a separate axis from injection) | 0.9028 |
 
17
 
18
  The recommended runtime configuration is `combined_max` — the elementwise
19
  max of `ensemble_v4_persona` and `v3`. The two fail in opposite directions
 
14
  | `ensemble_v4_persona` | From-scratch ensemble: char-CNN + BiLSTM-attention + scratch transformer, 12.3M params | 0.8278 |
15
  | `v3` | DistilBERT after the Track B online-retraining cycle, 66M params | 0.7875 |
16
  | `harm_detector` | Content-harm classifier (a separate axis from injection) | 0.9028 |
17
+ | `ensemble_v5_fpr` | Persona-rebalanced ensemble — lower FPR (0.328 vs 0.363), misses one canonical short attack | 0.8237 |
18
 
19
  The recommended runtime configuration is `combined_max` — the elementwise
20
  max of `ensemble_v4_persona` and `v3`. The two fail in opposite directions