n3sw_b4fp2 — RAI safety classifier (Atlassian responsible-ai campaign)

• Base: nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
• Method: full-SFT (final merged model; optimizer states not saved by the trainer)
• Arm / iteration: n3sw_b4fp2 / n3sweet
• Contents: model weights (root) · eval/ = raw inference outputs on the eval sets (v14, hello_v2_filtered, v200, robustnessv2) under policy prompts v3_1b / v3_1c · artifacts/ = training log
• Eval-inference files uploaded: 10