=== Laguna-S-2.1-RFA ===
arch: laguna
codebook: [-127, -104, -83, -65, -49, -35, -22, -10, 1, 13, 25, 38, 53, 69, 89, 113]
rotation: hadamard16

[integrity] shards=13 missing=none
[integrity] index total_size=71.16GB  on-disk safetensors sum=71.17GB
[integrity] tensors: index=109249 headers=109249 OK

[coverage] quantized expert-mods=0 linear-mods=36240 fp16-protected=0 copied=529
[coverage] missing/bad: 0

[bpw] quant-target params=114.10B  rfa bytes=64.25GB  -> 4.504 bits/weight
[size] total=71.16GB = rfa 64.25GB + copied(bf16/other) 6.91GB

[fidelity] dequant vs source (relFro / SQNR):
   model.layers.0.mlp.down_proj  relFro=6.150%  SQNR=24.2 dB
   model.layers.0.mlp.gate_proj  relFro=6.311%  SQNR=24.0 dB
   model.layers.0.mlp.up_proj  relFro=6.304%  SQNR=24.0 dB
   model.layers.24.mlp.experts.0.down_proj  relFro=6.328%  SQNR=24.0 dB
   model.layers.24.mlp.experts.0.gate_proj  relFro=6.334%  SQNR=24.0 dB
   model.layers.24.mlp.experts.0.up_proj  relFro=6.335%  SQNR=24.0 dB
   model.layers.47.mlp.experts.0.down_proj  relFro=6.338%  SQNR=24.0 dB
   model.layers.47.mlp.experts.0.gate_proj  relFro=6.340%  SQNR=24.0 dB
   model.layers.47.mlp.experts.0.up_proj  relFro=6.336%  SQNR=24.0 dB

DONE