| { |
| "producer": { |
| "name": "jev-judge scripts/export_nvfp4_experts.py" |
| }, |
| "quantization": { |
| "quant_algo": "NVFP4", |
| "kv_cache_quant_algo": null, |
| "group_size": 16, |
| "exclude_modules": [ |
| "lm_head", |
| "model.visual*", |
| "mtp*", |
| "model.language_model.layers.0.self_attn*", |
| "model.language_model.layers.0.linear_attn*", |
| "model.language_model.layers.0.mlp.gate", |
| "model.language_model.layers.0.mlp.shared_expert*", |
| "model.language_model.layers.1.self_attn*", |
| "model.language_model.layers.1.linear_attn*", |
| "model.language_model.layers.1.mlp.gate", |
| "model.language_model.layers.1.mlp.shared_expert*", |
| "model.language_model.layers.2.self_attn*", |
| "model.language_model.layers.2.linear_attn*", |
| "model.language_model.layers.2.mlp.gate", |
| "model.language_model.layers.2.mlp.shared_expert*", |
| "model.language_model.layers.3.self_attn*", |
| "model.language_model.layers.3.linear_attn*", |
| "model.language_model.layers.3.mlp.gate", |
| "model.language_model.layers.3.mlp.shared_expert*", |
| "model.language_model.layers.4.self_attn*", |
| "model.language_model.layers.4.linear_attn*", |
| "model.language_model.layers.4.mlp.gate", |
| "model.language_model.layers.4.mlp.shared_expert*", |
| "model.language_model.layers.5.self_attn*", |
| "model.language_model.layers.5.linear_attn*", |
| "model.language_model.layers.5.mlp.gate", |
| "model.language_model.layers.5.mlp.shared_expert*", |
| "model.language_model.layers.6.self_attn*", |
| "model.language_model.layers.6.linear_attn*", |
| "model.language_model.layers.6.mlp.gate", |
| "model.language_model.layers.6.mlp.shared_expert*", |
| "model.language_model.layers.7.self_attn*", |
| "model.language_model.layers.7.linear_attn*", |
| "model.language_model.layers.7.mlp.gate", |
| "model.language_model.layers.7.mlp.shared_expert*", |
| "model.language_model.layers.8.self_attn*", |
| "model.language_model.layers.8.linear_attn*", |
| "model.language_model.layers.8.mlp.gate", |
| "model.language_model.layers.8.mlp.shared_expert*", |
| "model.language_model.layers.9.self_attn*", |
| "model.language_model.layers.9.linear_attn*", |
| "model.language_model.layers.9.mlp.gate", |
| "model.language_model.layers.9.mlp.shared_expert*", |
| "model.language_model.layers.10.self_attn*", |
| "model.language_model.layers.10.linear_attn*", |
| "model.language_model.layers.10.mlp.gate", |
| "model.language_model.layers.10.mlp.shared_expert*", |
| "model.language_model.layers.11.self_attn*", |
| "model.language_model.layers.11.linear_attn*", |
| "model.language_model.layers.11.mlp.gate", |
| "model.language_model.layers.11.mlp.shared_expert*", |
| "model.language_model.layers.12.self_attn*", |
| "model.language_model.layers.12.linear_attn*", |
| "model.language_model.layers.12.mlp.gate", |
| "model.language_model.layers.12.mlp.shared_expert*", |
| "model.language_model.layers.13.self_attn*", |
| "model.language_model.layers.13.linear_attn*", |
| "model.language_model.layers.13.mlp.gate", |
| "model.language_model.layers.13.mlp.shared_expert*", |
| "model.language_model.layers.14.self_attn*", |
| "model.language_model.layers.14.linear_attn*", |
| "model.language_model.layers.14.mlp.gate", |
| "model.language_model.layers.14.mlp.shared_expert*", |
| "model.language_model.layers.15.self_attn*", |
| "model.language_model.layers.15.linear_attn*", |
| "model.language_model.layers.15.mlp.gate", |
| "model.language_model.layers.15.mlp.shared_expert*", |
| "model.language_model.layers.16.self_attn*", |
| "model.language_model.layers.16.linear_attn*", |
| "model.language_model.layers.16.mlp.gate", |
| "model.language_model.layers.16.mlp.shared_expert*", |
| "model.language_model.layers.17.self_attn*", |
| "model.language_model.layers.17.linear_attn*", |
| "model.language_model.layers.17.mlp.gate", |
| "model.language_model.layers.17.mlp.shared_expert*", |
| "model.language_model.layers.18.self_attn*", |
| "model.language_model.layers.18.linear_attn*", |
| "model.language_model.layers.18.mlp.gate", |
| "model.language_model.layers.18.mlp.shared_expert*", |
| "model.language_model.layers.19.self_attn*", |
| "model.language_model.layers.19.linear_attn*", |
| "model.language_model.layers.19.mlp.gate", |
| "model.language_model.layers.19.mlp.shared_expert*", |
| "model.language_model.layers.20.self_attn*", |
| "model.language_model.layers.20.linear_attn*", |
| "model.language_model.layers.20.mlp.gate", |
| "model.language_model.layers.20.mlp.shared_expert*", |
| "model.language_model.layers.21.self_attn*", |
| "model.language_model.layers.21.linear_attn*", |
| "model.language_model.layers.21.mlp.gate", |
| "model.language_model.layers.21.mlp.shared_expert*", |
| "model.language_model.layers.22.self_attn*", |
| "model.language_model.layers.22.linear_attn*", |
| "model.language_model.layers.22.mlp.gate", |
| "model.language_model.layers.22.mlp.shared_expert*", |
| "model.language_model.layers.23.self_attn*", |
| "model.language_model.layers.23.linear_attn*", |
| "model.language_model.layers.23.mlp.gate", |
| "model.language_model.layers.23.mlp.shared_expert*", |
| "model.language_model.layers.24.self_attn*", |
| "model.language_model.layers.24.linear_attn*", |
| "model.language_model.layers.24.mlp.gate", |
| "model.language_model.layers.24.mlp.shared_expert*", |
| "model.language_model.layers.25.self_attn*", |
| "model.language_model.layers.25.linear_attn*", |
| "model.language_model.layers.25.mlp.gate", |
| "model.language_model.layers.25.mlp.shared_expert*", |
| "model.language_model.layers.26.self_attn*", |
| "model.language_model.layers.26.linear_attn*", |
| "model.language_model.layers.26.mlp.gate", |
| "model.language_model.layers.26.mlp.shared_expert*", |
| "model.language_model.layers.27.self_attn*", |
| "model.language_model.layers.27.linear_attn*", |
| "model.language_model.layers.27.mlp.gate", |
| "model.language_model.layers.27.mlp.shared_expert*", |
| "model.language_model.layers.28.self_attn*", |
| "model.language_model.layers.28.linear_attn*", |
| "model.language_model.layers.28.mlp.gate", |
| "model.language_model.layers.28.mlp.shared_expert*", |
| "model.language_model.layers.29.self_attn*", |
| "model.language_model.layers.29.linear_attn*", |
| "model.language_model.layers.29.mlp.gate", |
| "model.language_model.layers.29.mlp.shared_expert*", |
| "model.language_model.layers.30.self_attn*", |
| "model.language_model.layers.30.linear_attn*", |
| "model.language_model.layers.30.mlp.gate", |
| "model.language_model.layers.30.mlp.shared_expert*", |
| "model.language_model.layers.31.self_attn*", |
| "model.language_model.layers.31.linear_attn*", |
| "model.language_model.layers.31.mlp.gate", |
| "model.language_model.layers.31.mlp.shared_expert*", |
| "model.language_model.layers.32.self_attn*", |
| "model.language_model.layers.32.linear_attn*", |
| "model.language_model.layers.32.mlp.gate", |
| "model.language_model.layers.32.mlp.shared_expert*", |
| "model.language_model.layers.33.self_attn*", |
| "model.language_model.layers.33.linear_attn*", |
| "model.language_model.layers.33.mlp.gate", |
| "model.language_model.layers.33.mlp.shared_expert*", |
| "model.language_model.layers.34.self_attn*", |
| "model.language_model.layers.34.linear_attn*", |
| "model.language_model.layers.34.mlp.gate", |
| "model.language_model.layers.34.mlp.shared_expert*", |
| "model.language_model.layers.35.self_attn*", |
| "model.language_model.layers.35.linear_attn*", |
| "model.language_model.layers.35.mlp.gate", |
| "model.language_model.layers.35.mlp.shared_expert*", |
| "model.language_model.layers.36.self_attn*", |
| "model.language_model.layers.36.linear_attn*", |
| "model.language_model.layers.36.mlp.gate", |
| "model.language_model.layers.36.mlp.shared_expert*", |
| "model.language_model.layers.37.self_attn*", |
| "model.language_model.layers.37.linear_attn*", |
| "model.language_model.layers.37.mlp.gate", |
| "model.language_model.layers.37.mlp.shared_expert*", |
| "model.language_model.layers.38.self_attn*", |
| "model.language_model.layers.38.linear_attn*", |
| "model.language_model.layers.38.mlp.gate", |
| "model.language_model.layers.38.mlp.shared_expert*", |
| "model.language_model.layers.39.self_attn*", |
| "model.language_model.layers.39.linear_attn*", |
| "model.language_model.layers.39.mlp.gate", |
| "model.language_model.layers.39.mlp.shared_expert*" |
| ] |
| } |
| } |
