I build, break, and deploy AI systems.

Remove refusal behavior from a 30.7B multimodal model without losing a deployable format set.

Applied weight-level abliteration, then carried the same model lineage through BF16, ModelOpt NVFP4, and a GGUF K-quant ladder. For multimodal NVFP4 serving, the vision tower, embedder, and lm_head stayed in BF16.

Fit a 34.7B Qwen3.5-MoE reasoning checkpoint onto a single Blackwell workstation without quantizing every subsystem.

Quantized routed experts to NVFP4 with NVIDIA ModelOpt; kept attention QKV, shared experts, and the vision encoder at higher precision.

Study refusal behavior in a 428B multimodal MoE while preserving its reasoning and routing structure.

Modified attention o_proj and every residual-writing down_proj across all 60 layers; released the result as 796 GB BF16 in 59 shards.