{
  "config_groups": {
    "group_0": {
      "targets": [
        "Linear"
      ],
      "weights": {
        "num_bits": 4,
        "type": "float",
        "symmetric": true,
        "group_size": 32,
        "strategy": "group",
        "block_structure": null,
        "dynamic": false,
        "actorder": null,
        "scale_dtype": "torch.uint8",
        "zp_dtype": null,
        "observer": "memoryless_minmax",
        "observer_kwargs": {}
      },
      "input_activations": {
        "num_bits": 4,
        "type": "float",
        "symmetric": true,
        "group_size": 32,
        "strategy": "group",
        "block_structure": null,
        "dynamic": true,
        "actorder": null,
        "scale_dtype": "torch.uint8",
        "zp_dtype": null,
        "observer": null,
        "observer_kwargs": {}
      },
      "output_activations": null,
      "format": null
    }
  },
  "quant_method": "compressed-tensors",
  "kv_cache_scheme": null,
  "format": "mxfp4-pack-quantized",
  "quantization_status": "compressed",
  "global_compression_ratio": null,
  "ignore": [
    "language_model.model.layers.44.mlp.gate",
    "language_model.model.layers.44.mlp.shared_experts.down_proj",
    "language_model.model.layers.44.mlp.shared_experts.gate_proj",
    "language_model.model.layers.44.mlp.shared_experts.up_proj",
    "language_model.model.layers.44.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.44.self_attn.kv_b_proj",
    "language_model.model.layers.44.self_attn.o_proj",
    "language_model.model.layers.44.self_attn.q_a_proj",
    "language_model.model.layers.44.self_attn.q_b_proj",
    "language_model.model.layers.17.mlp.gate",
    "language_model.model.layers.17.mlp.shared_experts.down_proj",
    "language_model.model.layers.17.mlp.shared_experts.gate_proj",
    "language_model.model.layers.17.mlp.shared_experts.up_proj",
    "language_model.model.layers.17.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.17.self_attn.kv_b_proj",
    "language_model.model.layers.17.self_attn.o_proj",
    "language_model.model.layers.17.self_attn.q_a_proj",
    "language_model.model.layers.17.self_attn.q_b_proj",
    "language_model.model.layers.3.mlp.gate",
    "language_model.model.layers.3.mlp.shared_experts.down_proj",
    "language_model.model.layers.3.mlp.shared_experts.gate_proj",
    "language_model.model.layers.3.mlp.shared_experts.up_proj",
    "language_model.model.layers.3.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.3.self_attn.kv_b_proj",
    "language_model.model.layers.3.self_attn.o_proj",
    "language_model.model.layers.3.self_attn.q_a_proj",
    "language_model.model.layers.3.self_attn.q_b_proj",
    "language_model.model.layers.37.mlp.gate",
    "language_model.model.layers.37.mlp.shared_experts.down_proj",
    "language_model.model.layers.37.mlp.shared_experts.gate_proj",
    "language_model.model.layers.37.mlp.shared_experts.up_proj",
    "language_model.model.layers.37.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.37.self_attn.kv_b_proj",
    "language_model.model.layers.37.self_attn.o_proj",
    "language_model.model.layers.37.self_attn.q_a_proj",
    "language_model.model.layers.37.self_attn.q_b_proj",
    "language_model.model.layers.14.mlp.gate",
    "language_model.model.layers.14.mlp.shared_experts.down_proj",
    "language_model.model.layers.14.mlp.shared_experts.gate_proj",
    "language_model.model.layers.14.mlp.shared_experts.up_proj",
    "language_model.model.layers.14.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.14.self_attn.kv_b_proj",
    "language_model.model.layers.14.self_attn.o_proj",
    "language_model.model.layers.14.self_attn.q_a_proj",
    "language_model.model.layers.14.self_attn.q_b_proj",
    "language_model.model.layers.53.mlp.gate",
    "language_model.model.layers.53.mlp.shared_experts.down_proj",
    "language_model.model.layers.53.mlp.shared_experts.gate_proj",
    "language_model.model.layers.53.mlp.shared_experts.up_proj",
    "language_model.model.layers.53.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.53.self_attn.kv_b_proj",
    "language_model.model.layers.53.self_attn.o_proj",
    "language_model.model.layers.53.self_attn.q_a_proj",
    "language_model.model.layers.53.self_attn.q_b_proj",
    "language_model.model.layers.43.mlp.gate",
    "language_model.model.layers.43.mlp.shared_experts.down_proj",
    "language_model.model.layers.43.mlp.shared_experts.gate_proj",
    "language_model.model.layers.43.mlp.shared_experts.up_proj",
    "language_model.model.layers.43.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.43.self_attn.kv_b_proj",
    "language_model.model.layers.43.self_attn.o_proj",
    "language_model.model.layers.43.self_attn.q_a_proj",
    "language_model.model.layers.43.self_attn.q_b_proj",
    "language_model.model.layers.27.mlp.gate",
    "language_model.model.layers.27.mlp.shared_experts.down_proj",
    "language_model.model.layers.27.mlp.shared_experts.gate_proj",
    "language_model.model.layers.27.mlp.shared_experts.up_proj",
    "language_model.model.layers.27.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.27.self_attn.kv_b_proj",
    "language_model.model.layers.27.self_attn.o_proj",
    "language_model.model.layers.27.self_attn.q_a_proj",
    "language_model.model.layers.27.self_attn.q_b_proj",
    "language_model.model.layers.31.mlp.gate",
    "language_model.model.layers.31.mlp.shared_experts.down_proj",
    "language_model.model.layers.31.mlp.shared_experts.gate_proj",
    "language_model.model.layers.31.mlp.shared_experts.up_proj",
    "language_model.model.layers.31.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.31.self_attn.kv_b_proj",
    "language_model.model.layers.31.self_attn.o_proj",
    "language_model.model.layers.31.self_attn.q_a_proj",
    "language_model.model.layers.31.self_attn.q_b_proj",
    "language_model.model.layers.48.mlp.gate",
    "language_model.model.layers.48.mlp.shared_experts.down_proj",
    "language_model.model.layers.48.mlp.shared_experts.gate_proj",
    "language_model.model.layers.48.mlp.shared_experts.up_proj",
    "language_model.model.layers.48.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.48.self_attn.kv_b_proj",
    "language_model.model.layers.48.self_attn.o_proj",
    "language_model.model.layers.48.self_attn.q_a_proj",
    "language_model.model.layers.48.self_attn.q_b_proj",
    "mm_projector.proj.0",
    "mm_projector.proj.2",
    "vision_tower.encoder.blocks.0.mlp.fc0",
    "vision_tower.encoder.blocks.0.mlp.fc1",
    "vision_tower.encoder.blocks.0.wo",
    "vision_tower.encoder.blocks.0.wqkv",
    "vision_tower.encoder.blocks.1.mlp.fc0",
    "vision_tower.encoder.blocks.1.mlp.fc1",
    "vision_tower.encoder.blocks.1.wo",
    "vision_tower.encoder.blocks.1.wqkv",
    "vision_tower.encoder.blocks.10.mlp.fc0",
    "vision_tower.encoder.blocks.10.mlp.fc1",
    "vision_tower.encoder.blocks.10.wo",
    "vision_tower.encoder.blocks.10.wqkv",
    "vision_tower.encoder.blocks.11.mlp.fc0",
    "vision_tower.encoder.blocks.11.mlp.fc1",
    "vision_tower.encoder.blocks.11.wo",
    "vision_tower.encoder.blocks.11.wqkv",
    "vision_tower.encoder.blocks.12.mlp.fc0",
    "vision_tower.encoder.blocks.12.mlp.fc1",
    "vision_tower.encoder.blocks.12.wo",
    "vision_tower.encoder.blocks.12.wqkv",
    "vision_tower.encoder.blocks.13.mlp.fc0",
    "vision_tower.encoder.blocks.13.mlp.fc1",
    "vision_tower.encoder.blocks.13.wo",
    "vision_tower.encoder.blocks.13.wqkv",
    "vision_tower.encoder.blocks.14.mlp.fc0",
    "vision_tower.encoder.blocks.14.mlp.fc1",
    "vision_tower.encoder.blocks.14.wo",
    "vision_tower.encoder.blocks.14.wqkv",
    "vision_tower.encoder.blocks.15.mlp.fc0",
    "vision_tower.encoder.blocks.15.mlp.fc1",
    "vision_tower.encoder.blocks.15.wo",
    "vision_tower.encoder.blocks.15.wqkv",
    "vision_tower.encoder.blocks.16.mlp.fc0",
    "vision_tower.encoder.blocks.16.mlp.fc1",
    "vision_tower.encoder.blocks.16.wo",
    "vision_tower.encoder.blocks.16.wqkv",
    "vision_tower.encoder.blocks.17.mlp.fc0",
    "vision_tower.encoder.blocks.17.mlp.fc1",
    "vision_tower.encoder.blocks.17.wo",
    "vision_tower.encoder.blocks.17.wqkv",
    "vision_tower.encoder.blocks.18.mlp.fc0",
    "vision_tower.encoder.blocks.18.mlp.fc1",
    "vision_tower.encoder.blocks.18.wo",
    "vision_tower.encoder.blocks.18.wqkv",
    "vision_tower.encoder.blocks.19.mlp.fc0",
    "vision_tower.encoder.blocks.19.mlp.fc1",
    "vision_tower.encoder.blocks.19.wo",
    "vision_tower.encoder.blocks.19.wqkv",
    "vision_tower.encoder.blocks.2.mlp.fc0",
    "vision_tower.encoder.blocks.2.mlp.fc1",
    "vision_tower.encoder.blocks.2.wo",
    "vision_tower.encoder.blocks.2.wqkv",
    "vision_tower.encoder.blocks.20.mlp.fc0",
    "vision_tower.encoder.blocks.20.mlp.fc1",
    "vision_tower.encoder.blocks.20.wo",
    "vision_tower.encoder.blocks.20.wqkv",
    "vision_tower.encoder.blocks.21.mlp.fc0",
    "vision_tower.encoder.blocks.21.mlp.fc1",
    "vision_tower.encoder.blocks.21.wo",
    "vision_tower.encoder.blocks.21.wqkv",
    "vision_tower.encoder.blocks.22.mlp.fc0",
    "vision_tower.encoder.blocks.22.mlp.fc1",
    "vision_tower.encoder.blocks.22.wo",
    "vision_tower.encoder.blocks.22.wqkv",
    "vision_tower.encoder.blocks.23.mlp.fc0",
    "vision_tower.encoder.blocks.23.mlp.fc1",
    "vision_tower.encoder.blocks.23.wo",
    "vision_tower.encoder.blocks.23.wqkv",
    "vision_tower.encoder.blocks.24.mlp.fc0",
    "vision_tower.encoder.blocks.24.mlp.fc1",
    "vision_tower.encoder.blocks.24.wo",
    "vision_tower.encoder.blocks.24.wqkv",
    "vision_tower.encoder.blocks.25.mlp.fc0",
    "vision_tower.encoder.blocks.25.mlp.fc1",
    "vision_tower.encoder.blocks.25.wo",
    "vision_tower.encoder.blocks.25.wqkv",
    "vision_tower.encoder.blocks.26.mlp.fc0",
    "vision_tower.encoder.blocks.26.mlp.fc1",
    "vision_tower.encoder.blocks.26.wo",
    "vision_tower.encoder.blocks.26.wqkv",
    "vision_tower.encoder.blocks.3.mlp.fc0",
    "vision_tower.encoder.blocks.3.mlp.fc1",
    "vision_tower.encoder.blocks.3.wo",
    "vision_tower.encoder.blocks.3.wqkv",
    "vision_tower.encoder.blocks.4.mlp.fc0",
    "vision_tower.encoder.blocks.4.mlp.fc1",
    "vision_tower.encoder.blocks.4.wo",
    "vision_tower.encoder.blocks.4.wqkv",
    "vision_tower.encoder.blocks.5.mlp.fc0",
    "vision_tower.encoder.blocks.5.mlp.fc1",
    "vision_tower.encoder.blocks.5.wo",
    "vision_tower.encoder.blocks.5.wqkv",
    "vision_tower.encoder.blocks.6.mlp.fc0",
    "vision_tower.encoder.blocks.6.mlp.fc1",
    "vision_tower.encoder.blocks.6.wo",
    "vision_tower.encoder.blocks.6.wqkv",
    "vision_tower.encoder.blocks.7.mlp.fc0",
    "vision_tower.encoder.blocks.7.mlp.fc1",
    "vision_tower.encoder.blocks.7.wo",
    "vision_tower.encoder.blocks.7.wqkv",
    "vision_tower.encoder.blocks.8.mlp.fc0",
    "vision_tower.encoder.blocks.8.mlp.fc1",
    "vision_tower.encoder.blocks.8.wo",
    "vision_tower.encoder.blocks.8.wqkv",
    "vision_tower.encoder.blocks.9.mlp.fc0",
    "vision_tower.encoder.blocks.9.mlp.fc1",
    "vision_tower.encoder.blocks.9.wo",
    "vision_tower.encoder.blocks.9.wqkv",
    "vision_tower.patch_embed.pos_emb",
    "vision_tower.patch_embed.proj",
    "language_model.model.layers.33.mlp.gate",
    "language_model.model.layers.33.mlp.shared_experts.down_proj",
    "language_model.model.layers.33.mlp.shared_experts.gate_proj",
    "language_model.model.layers.33.mlp.shared_experts.up_proj",
    "language_model.model.layers.33.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.33.self_attn.kv_b_proj",
    "language_model.model.layers.33.self_attn.o_proj",
    "language_model.model.layers.33.self_attn.q_a_proj",
    "language_model.model.layers.33.self_attn.q_b_proj",
    "language_model.model.layers.26.mlp.gate",
    "language_model.model.layers.26.mlp.shared_experts.down_proj",
    "language_model.model.layers.26.mlp.shared_experts.gate_proj",
    "language_model.model.layers.26.mlp.shared_experts.up_proj",
    "language_model.model.layers.26.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.26.self_attn.kv_b_proj",
    "language_model.model.layers.26.self_attn.o_proj",
    "language_model.model.layers.26.self_attn.q_a_proj",
    "language_model.model.layers.26.self_attn.q_b_proj",
    "language_model.model.layers.36.mlp.gate",
    "language_model.model.layers.36.mlp.shared_experts.down_proj",
    "language_model.model.layers.36.mlp.shared_experts.gate_proj",
    "language_model.model.layers.36.mlp.shared_experts.up_proj",
    "language_model.model.layers.36.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.36.self_attn.kv_b_proj",
    "language_model.model.layers.36.self_attn.o_proj",
    "language_model.model.layers.36.self_attn.q_a_proj",
    "language_model.model.layers.36.self_attn.q_b_proj",
    "language_model.model.layers.11.mlp.gate",
    "language_model.model.layers.11.mlp.shared_experts.down_proj",
    "language_model.model.layers.11.mlp.shared_experts.gate_proj",
    "language_model.model.layers.11.mlp.shared_experts.up_proj",
    "language_model.model.layers.11.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.11.self_attn.kv_b_proj",
    "language_model.model.layers.11.self_attn.o_proj",
    "language_model.model.layers.11.self_attn.q_a_proj",
    "language_model.model.layers.11.self_attn.q_b_proj",
    "language_model.model.layers.59.mlp.gate",
    "language_model.model.layers.59.mlp.shared_experts.down_proj",
    "language_model.model.layers.59.mlp.shared_experts.gate_proj",
    "language_model.model.layers.59.mlp.shared_experts.up_proj",
    "language_model.model.layers.59.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.59.self_attn.kv_b_proj",
    "language_model.model.layers.59.self_attn.o_proj",
    "language_model.model.layers.59.self_attn.q_a_proj",
    "language_model.model.layers.59.self_attn.q_b_proj",
    "language_model.model.layers.40.mlp.gate",
    "language_model.model.layers.40.mlp.shared_experts.down_proj",
    "language_model.model.layers.40.mlp.shared_experts.gate_proj",
    "language_model.model.layers.40.mlp.shared_experts.up_proj",
    "language_model.model.layers.40.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.40.self_attn.kv_b_proj",
    "language_model.model.layers.40.self_attn.o_proj",
    "language_model.model.layers.40.self_attn.q_a_proj",
    "language_model.model.layers.40.self_attn.q_b_proj",
    "language_model.model.layers.34.mlp.gate",
    "language_model.model.layers.34.mlp.shared_experts.down_proj",
    "language_model.model.layers.34.mlp.shared_experts.gate_proj",
    "language_model.model.layers.34.mlp.shared_experts.up_proj",
    "language_model.model.layers.34.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.34.self_attn.kv_b_proj",
    "language_model.model.layers.34.self_attn.o_proj",
    "language_model.model.layers.34.self_attn.q_a_proj",
    "language_model.model.layers.34.self_attn.q_b_proj",
    "language_model.model.layers.25.mlp.gate",
    "language_model.model.layers.25.mlp.shared_experts.down_proj",
    "language_model.model.layers.25.mlp.shared_experts.gate_proj",
    "language_model.model.layers.25.mlp.shared_experts.up_proj",
    "language_model.model.layers.25.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.25.self_attn.kv_b_proj",
    "language_model.model.layers.25.self_attn.o_proj",
    "language_model.model.layers.25.self_attn.q_a_proj",
    "language_model.model.layers.25.self_attn.q_b_proj",
    "language_model.model.layers.51.mlp.gate",
    "language_model.model.layers.51.mlp.shared_experts.down_proj",
    "language_model.model.layers.51.mlp.shared_experts.gate_proj",
    "language_model.model.layers.51.mlp.shared_experts.up_proj",
    "language_model.model.layers.51.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.51.self_attn.kv_b_proj",
    "language_model.model.layers.51.self_attn.o_proj",
    "language_model.model.layers.51.self_attn.q_a_proj",
    "language_model.model.layers.51.self_attn.q_b_proj",
    "language_model.model.layers.49.mlp.gate",
    "language_model.model.layers.49.mlp.shared_experts.down_proj",
    "language_model.model.layers.49.mlp.shared_experts.gate_proj",
    "language_model.model.layers.49.mlp.shared_experts.up_proj",
    "language_model.model.layers.49.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.49.self_attn.kv_b_proj",
    "language_model.model.layers.49.self_attn.o_proj",
    "language_model.model.layers.49.self_attn.q_a_proj",
    "language_model.model.layers.49.self_attn.q_b_proj",
    "language_model.model.layers.7.mlp.gate",
    "language_model.model.layers.7.mlp.shared_experts.down_proj",
    "language_model.model.layers.7.mlp.shared_experts.gate_proj",
    "language_model.model.layers.7.mlp.shared_experts.up_proj",
    "language_model.model.layers.7.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.7.self_attn.kv_b_proj",
    "language_model.model.layers.7.self_attn.o_proj",
    "language_model.model.layers.7.self_attn.q_a_proj",
    "language_model.model.layers.7.self_attn.q_b_proj",
    "language_model.model.layers.2.mlp.gate",
    "language_model.model.layers.2.mlp.shared_experts.down_proj",
    "language_model.model.layers.2.mlp.shared_experts.gate_proj",
    "language_model.model.layers.2.mlp.shared_experts.up_proj",
    "language_model.model.layers.2.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.2.self_attn.kv_b_proj",
    "language_model.model.layers.2.self_attn.o_proj",
    "language_model.model.layers.2.self_attn.q_a_proj",
    "language_model.model.layers.2.self_attn.q_b_proj",
    "language_model.model.layers.32.mlp.gate",
    "language_model.model.layers.32.mlp.shared_experts.down_proj",
    "language_model.model.layers.32.mlp.shared_experts.gate_proj",
    "language_model.model.layers.32.mlp.shared_experts.up_proj",
    "language_model.model.layers.32.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.32.self_attn.kv_b_proj",
    "language_model.model.layers.32.self_attn.o_proj",
    "language_model.model.layers.32.self_attn.q_a_proj",
    "language_model.model.layers.32.self_attn.q_b_proj",
    "language_model.model.layers.6.mlp.gate",
    "language_model.model.layers.6.mlp.shared_experts.down_proj",
    "language_model.model.layers.6.mlp.shared_experts.gate_proj",
    "language_model.model.layers.6.mlp.shared_experts.up_proj",
    "language_model.model.layers.6.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.6.self_attn.kv_b_proj",
    "language_model.model.layers.6.self_attn.o_proj",
    "language_model.model.layers.6.self_attn.q_a_proj",
    "language_model.model.layers.6.self_attn.q_b_proj",
    "language_model.model.layers.30.mlp.gate",
    "language_model.model.layers.30.mlp.shared_experts.down_proj",
    "language_model.model.layers.30.mlp.shared_experts.gate_proj",
    "language_model.model.layers.30.mlp.shared_experts.up_proj",
    "language_model.model.layers.30.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.30.self_attn.kv_b_proj",
    "language_model.model.layers.30.self_attn.o_proj",
    "language_model.model.layers.30.self_attn.q_a_proj",
    "language_model.model.layers.30.self_attn.q_b_proj",
    "language_model.model.layers.45.mlp.gate",
    "language_model.model.layers.45.mlp.shared_experts.down_proj",
    "language_model.model.layers.45.mlp.shared_experts.gate_proj",
    "language_model.model.layers.45.mlp.shared_experts.up_proj",
    "language_model.model.layers.45.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.45.self_attn.kv_b_proj",
    "language_model.model.layers.45.self_attn.o_proj",
    "language_model.model.layers.45.self_attn.q_a_proj",
    "language_model.model.layers.45.self_attn.q_b_proj",
    "language_model.model.layers.55.mlp.gate",
    "language_model.model.layers.55.mlp.shared_experts.down_proj",
    "language_model.model.layers.55.mlp.shared_experts.gate_proj",
    "language_model.model.layers.55.mlp.shared_experts.up_proj",
    "language_model.model.layers.55.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.55.self_attn.kv_b_proj",
    "language_model.model.layers.55.self_attn.o_proj",
    "language_model.model.layers.55.self_attn.q_a_proj",
    "language_model.model.layers.55.self_attn.q_b_proj",
    "language_model.model.layers.1.mlp.gate",
    "language_model.model.layers.1.mlp.shared_experts.down_proj",
    "language_model.model.layers.1.mlp.shared_experts.gate_proj",
    "language_model.model.layers.1.mlp.shared_experts.up_proj",
    "language_model.model.layers.1.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.1.self_attn.kv_b_proj",
    "language_model.model.layers.1.self_attn.o_proj",
    "language_model.model.layers.1.self_attn.q_a_proj",
    "language_model.model.layers.1.self_attn.q_b_proj",
    "language_model.model.layers.58.mlp.gate",
    "language_model.model.layers.58.mlp.shared_experts.down_proj",
    "language_model.model.layers.58.mlp.shared_experts.gate_proj",
    "language_model.model.layers.58.mlp.shared_experts.up_proj",
    "language_model.model.layers.58.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.58.self_attn.kv_b_proj",
    "language_model.model.layers.58.self_attn.o_proj",
    "language_model.model.layers.58.self_attn.q_a_proj",
    "language_model.model.layers.58.self_attn.q_b_proj",
    "language_model.model.layers.29.mlp.gate",
    "language_model.model.layers.29.mlp.shared_experts.down_proj",
    "language_model.model.layers.29.mlp.shared_experts.gate_proj",
    "language_model.model.layers.29.mlp.shared_experts.up_proj",
    "language_model.model.layers.29.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.29.self_attn.kv_b_proj",
    "language_model.model.layers.29.self_attn.o_proj",
    "language_model.model.layers.29.self_attn.q_a_proj",
    "language_model.model.layers.29.self_attn.q_b_proj",
    "language_model.model.layers.0.mlp.down_proj",
    "language_model.model.layers.0.mlp.gate_proj",
    "language_model.model.layers.0.mlp.up_proj",
    "language_model.model.layers.0.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.0.self_attn.kv_b_proj",
    "language_model.model.layers.0.self_attn.o_proj",
    "language_model.model.layers.0.self_attn.q_a_proj",
    "language_model.model.layers.0.self_attn.q_b_proj",
    "language_model.lm_head",
    "language_model.model.embed_tokens",
    "language_model.model.layers.21.mlp.gate",
    "language_model.model.layers.21.mlp.shared_experts.down_proj",
    "language_model.model.layers.21.mlp.shared_experts.gate_proj",
    "language_model.model.layers.21.mlp.shared_experts.up_proj",
    "language_model.model.layers.21.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.21.self_attn.kv_b_proj",
    "language_model.model.layers.21.self_attn.o_proj",
    "language_model.model.layers.21.self_attn.q_a_proj",
    "language_model.model.layers.21.self_attn.q_b_proj",
    "language_model.model.layers.24.mlp.gate",
    "language_model.model.layers.24.mlp.shared_experts.down_proj",
    "language_model.model.layers.24.mlp.shared_experts.gate_proj",
    "language_model.model.layers.24.mlp.shared_experts.up_proj",
    "language_model.model.layers.24.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.24.self_attn.kv_b_proj",
    "language_model.model.layers.24.self_attn.o_proj",
    "language_model.model.layers.24.self_attn.q_a_proj",
    "language_model.model.layers.24.self_attn.q_b_proj",
    "language_model.model.layers.39.mlp.gate",
    "language_model.model.layers.39.mlp.shared_experts.down_proj",
    "language_model.model.layers.39.mlp.shared_experts.gate_proj",
    "language_model.model.layers.39.mlp.shared_experts.up_proj",
    "language_model.model.layers.39.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.39.self_attn.kv_b_proj",
    "language_model.model.layers.39.self_attn.o_proj",
    "language_model.model.layers.39.self_attn.q_a_proj",
    "language_model.model.layers.39.self_attn.q_b_proj",
    "language_model.model.layers.50.mlp.gate",
    "language_model.model.layers.50.mlp.shared_experts.down_proj",
    "language_model.model.layers.50.mlp.shared_experts.gate_proj",
    "language_model.model.layers.50.mlp.shared_experts.up_proj",
    "language_model.model.layers.50.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.50.self_attn.kv_b_proj",
    "language_model.model.layers.50.self_attn.o_proj",
    "language_model.model.layers.50.self_attn.q_a_proj",
    "language_model.model.layers.50.self_attn.q_b_proj",
    "language_model.model.layers.46.mlp.gate",
    "language_model.model.layers.46.mlp.shared_experts.down_proj",
    "language_model.model.layers.46.mlp.shared_experts.gate_proj",
    "language_model.model.layers.46.mlp.shared_experts.up_proj",
    "language_model.model.layers.46.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.46.self_attn.kv_b_proj",
    "language_model.model.layers.46.self_attn.o_proj",
    "language_model.model.layers.46.self_attn.q_a_proj",
    "language_model.model.layers.46.self_attn.q_b_proj",
    "language_model.model.layers.10.mlp.gate",
    "language_model.model.layers.10.mlp.shared_experts.down_proj",
    "language_model.model.layers.10.mlp.shared_experts.gate_proj",
    "language_model.model.layers.10.mlp.shared_experts.up_proj",
    "language_model.model.layers.10.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.10.self_attn.kv_b_proj",
    "language_model.model.layers.10.self_attn.o_proj",
    "language_model.model.layers.10.self_attn.q_a_proj",
    "language_model.model.layers.10.self_attn.q_b_proj",
    "language_model.model.layers.18.mlp.gate",
    "language_model.model.layers.18.mlp.shared_experts.down_proj",
    "language_model.model.layers.18.mlp.shared_experts.gate_proj",
    "language_model.model.layers.18.mlp.shared_experts.up_proj",
    "language_model.model.layers.18.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.18.self_attn.kv_b_proj",
    "language_model.model.layers.18.self_attn.o_proj",
    "language_model.model.layers.18.self_attn.q_a_proj",
    "language_model.model.layers.18.self_attn.q_b_proj",
    "language_model.model.layers.5.mlp.gate",
    "language_model.model.layers.5.mlp.shared_experts.down_proj",
    "language_model.model.layers.5.mlp.shared_experts.gate_proj",
    "language_model.model.layers.5.mlp.shared_experts.up_proj",
    "language_model.model.layers.5.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.5.self_attn.kv_b_proj",
    "language_model.model.layers.5.self_attn.o_proj",
    "language_model.model.layers.5.self_attn.q_a_proj",
    "language_model.model.layers.5.self_attn.q_b_proj",
    "language_model.model.layers.41.mlp.gate",
    "language_model.model.layers.41.mlp.shared_experts.down_proj",
    "language_model.model.layers.41.mlp.shared_experts.gate_proj",
    "language_model.model.layers.41.mlp.shared_experts.up_proj",
    "language_model.model.layers.41.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.41.self_attn.kv_b_proj",
    "language_model.model.layers.41.self_attn.o_proj",
    "language_model.model.layers.41.self_attn.q_a_proj",
    "language_model.model.layers.41.self_attn.q_b_proj",
    "language_model.model.layers.4.mlp.gate",
    "language_model.model.layers.4.mlp.shared_experts.down_proj",
    "language_model.model.layers.4.mlp.shared_experts.gate_proj",
    "language_model.model.layers.4.mlp.shared_experts.up_proj",
    "language_model.model.layers.4.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.4.self_attn.kv_b_proj",
    "language_model.model.layers.4.self_attn.o_proj",
    "language_model.model.layers.4.self_attn.q_a_proj",
    "language_model.model.layers.4.self_attn.q_b_proj",
    "language_model.model.layers.38.mlp.gate",
    "language_model.model.layers.38.mlp.shared_experts.down_proj",
    "language_model.model.layers.38.mlp.shared_experts.gate_proj",
    "language_model.model.layers.38.mlp.shared_experts.up_proj",
    "language_model.model.layers.38.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.38.self_attn.kv_b_proj",
    "language_model.model.layers.38.self_attn.o_proj",
    "language_model.model.layers.38.self_attn.q_a_proj",
    "language_model.model.layers.38.self_attn.q_b_proj",
    "language_model.model.layers.12.mlp.gate",
    "language_model.model.layers.12.mlp.shared_experts.down_proj",
    "language_model.model.layers.12.mlp.shared_experts.gate_proj",
    "language_model.model.layers.12.mlp.shared_experts.up_proj",
    "language_model.model.layers.12.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.12.self_attn.kv_b_proj",
    "language_model.model.layers.12.self_attn.o_proj",
    "language_model.model.layers.12.self_attn.q_a_proj",
    "language_model.model.layers.12.self_attn.q_b_proj",
    "language_model.model.layers.15.mlp.gate",
    "language_model.model.layers.15.mlp.shared_experts.down_proj",
    "language_model.model.layers.15.mlp.shared_experts.gate_proj",
    "language_model.model.layers.15.mlp.shared_experts.up_proj",
    "language_model.model.layers.15.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.15.self_attn.kv_b_proj",
    "language_model.model.layers.15.self_attn.o_proj",
    "language_model.model.layers.15.self_attn.q_a_proj",
    "language_model.model.layers.15.self_attn.q_b_proj",
    "language_model.model.layers.52.mlp.gate",
    "language_model.model.layers.52.mlp.shared_experts.down_proj",
    "language_model.model.layers.52.mlp.shared_experts.gate_proj",
    "language_model.model.layers.52.mlp.shared_experts.up_proj",
    "language_model.model.layers.52.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.52.self_attn.kv_b_proj",
    "language_model.model.layers.52.self_attn.o_proj",
    "language_model.model.layers.52.self_attn.q_a_proj",
    "language_model.model.layers.52.self_attn.q_b_proj",
    "language_model.model.layers.13.mlp.gate",
    "language_model.model.layers.13.mlp.shared_experts.down_proj",
    "language_model.model.layers.13.mlp.shared_experts.gate_proj",
    "language_model.model.layers.13.mlp.shared_experts.up_proj",
    "language_model.model.layers.13.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.13.self_attn.kv_b_proj",
    "language_model.model.layers.13.self_attn.o_proj",
    "language_model.model.layers.13.self_attn.q_a_proj",
    "language_model.model.layers.13.self_attn.q_b_proj",
    "language_model.model.layers.60.mlp.gate",
    "language_model.model.layers.60.mlp.shared_experts.down_proj",
    "language_model.model.layers.60.mlp.shared_experts.gate_proj",
    "language_model.model.layers.60.mlp.shared_experts.up_proj",
    "language_model.model.layers.60.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.60.self_attn.kv_b_proj",
    "language_model.model.layers.60.self_attn.o_proj",
    "language_model.model.layers.60.self_attn.q_a_proj",
    "language_model.model.layers.60.self_attn.q_b_proj",
    "language_model.model.layers.35.mlp.gate",
    "language_model.model.layers.35.mlp.shared_experts.down_proj",
    "language_model.model.layers.35.mlp.shared_experts.gate_proj",
    "language_model.model.layers.35.mlp.shared_experts.up_proj",
    "language_model.model.layers.35.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.35.self_attn.kv_b_proj",
    "language_model.model.layers.35.self_attn.o_proj",
    "language_model.model.layers.35.self_attn.q_a_proj",
    "language_model.model.layers.35.self_attn.q_b_proj",
    "language_model.model.layers.19.mlp.gate",
    "language_model.model.layers.19.mlp.shared_experts.down_proj",
    "language_model.model.layers.19.mlp.shared_experts.gate_proj",
    "language_model.model.layers.19.mlp.shared_experts.up_proj",
    "language_model.model.layers.19.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.19.self_attn.kv_b_proj",
    "language_model.model.layers.19.self_attn.o_proj",
    "language_model.model.layers.19.self_attn.q_a_proj",
    "language_model.model.layers.19.self_attn.q_b_proj",
    "language_model.model.layers.47.mlp.gate",
    "language_model.model.layers.47.mlp.shared_experts.down_proj",
    "language_model.model.layers.47.mlp.shared_experts.gate_proj",
    "language_model.model.layers.47.mlp.shared_experts.up_proj",
    "language_model.model.layers.47.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.47.self_attn.kv_b_proj",
    "language_model.model.layers.47.self_attn.o_proj",
    "language_model.model.layers.47.self_attn.q_a_proj",
    "language_model.model.layers.47.self_attn.q_b_proj",
    "language_model.model.layers.56.mlp.gate",
    "language_model.model.layers.56.mlp.shared_experts.down_proj",
    "language_model.model.layers.56.mlp.shared_experts.gate_proj",
    "language_model.model.layers.56.mlp.shared_experts.up_proj",
    "language_model.model.layers.56.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.56.self_attn.kv_b_proj",
    "language_model.model.layers.56.self_attn.o_proj",
    "language_model.model.layers.56.self_attn.q_a_proj",
    "language_model.model.layers.56.self_attn.q_b_proj",
    "language_model.model.layers.57.mlp.gate",
    "language_model.model.layers.57.mlp.shared_experts.down_proj",
    "language_model.model.layers.57.mlp.shared_experts.gate_proj",
    "language_model.model.layers.57.mlp.shared_experts.up_proj",
    "language_model.model.layers.57.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.57.self_attn.kv_b_proj",
    "language_model.model.layers.57.self_attn.o_proj",
    "language_model.model.layers.57.self_attn.q_a_proj",
    "language_model.model.layers.57.self_attn.q_b_proj",
    "language_model.model.layers.54.mlp.gate",
    "language_model.model.layers.54.mlp.shared_experts.down_proj",
    "language_model.model.layers.54.mlp.shared_experts.gate_proj",
    "language_model.model.layers.54.mlp.shared_experts.up_proj",
    "language_model.model.layers.54.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.54.self_attn.kv_b_proj",
    "language_model.model.layers.54.self_attn.o_proj",
    "language_model.model.layers.54.self_attn.q_a_proj",
    "language_model.model.layers.54.self_attn.q_b_proj",
    "language_model.model.layers.16.mlp.gate",
    "language_model.model.layers.16.mlp.shared_experts.down_proj",
    "language_model.model.layers.16.mlp.shared_experts.gate_proj",
    "language_model.model.layers.16.mlp.shared_experts.up_proj",
    "language_model.model.layers.16.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.16.self_attn.kv_b_proj",
    "language_model.model.layers.16.self_attn.o_proj",
    "language_model.model.layers.16.self_attn.q_a_proj",
    "language_model.model.layers.16.self_attn.q_b_proj",
    "language_model.model.layers.8.mlp.gate",
    "language_model.model.layers.8.mlp.shared_experts.down_proj",
    "language_model.model.layers.8.mlp.shared_experts.gate_proj",
    "language_model.model.layers.8.mlp.shared_experts.up_proj",
    "language_model.model.layers.8.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.8.self_attn.kv_b_proj",
    "language_model.model.layers.8.self_attn.o_proj",
    "language_model.model.layers.8.self_attn.q_a_proj",
    "language_model.model.layers.8.self_attn.q_b_proj",
    "language_model.model.layers.20.mlp.gate",
    "language_model.model.layers.20.mlp.shared_experts.down_proj",
    "language_model.model.layers.20.mlp.shared_experts.gate_proj",
    "language_model.model.layers.20.mlp.shared_experts.up_proj",
    "language_model.model.layers.20.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.20.self_attn.kv_b_proj",
    "language_model.model.layers.20.self_attn.o_proj",
    "language_model.model.layers.20.self_attn.q_a_proj",
    "language_model.model.layers.20.self_attn.q_b_proj",
    "language_model.model.layers.42.mlp.gate",
    "language_model.model.layers.42.mlp.shared_experts.down_proj",
    "language_model.model.layers.42.mlp.shared_experts.gate_proj",
    "language_model.model.layers.42.mlp.shared_experts.up_proj",
    "language_model.model.layers.42.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.42.self_attn.kv_b_proj",
    "language_model.model.layers.42.self_attn.o_proj",
    "language_model.model.layers.42.self_attn.q_a_proj",
    "language_model.model.layers.42.self_attn.q_b_proj",
    "language_model.model.layers.9.mlp.gate",
    "language_model.model.layers.9.mlp.shared_experts.down_proj",
    "language_model.model.layers.9.mlp.shared_experts.gate_proj",
    "language_model.model.layers.9.mlp.shared_experts.up_proj",
    "language_model.model.layers.9.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.9.self_attn.kv_b_proj",
    "language_model.model.layers.9.self_attn.o_proj",
    "language_model.model.layers.9.self_attn.q_a_proj",
    "language_model.model.layers.9.self_attn.q_b_proj",
    "language_model.model.layers.28.mlp.gate",
    "language_model.model.layers.28.mlp.shared_experts.down_proj",
    "language_model.model.layers.28.mlp.shared_experts.gate_proj",
    "language_model.model.layers.28.mlp.shared_experts.up_proj",
    "language_model.model.layers.28.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.28.self_attn.kv_b_proj",
    "language_model.model.layers.28.self_attn.o_proj",
    "language_model.model.layers.28.self_attn.q_a_proj",
    "language_model.model.layers.28.self_attn.q_b_proj",
    "language_model.model.layers.23.mlp.gate",
    "language_model.model.layers.23.mlp.shared_experts.down_proj",
    "language_model.model.layers.23.mlp.shared_experts.gate_proj",
    "language_model.model.layers.23.mlp.shared_experts.up_proj",
    "language_model.model.layers.23.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.23.self_attn.kv_b_proj",
    "language_model.model.layers.23.self_attn.o_proj",
    "language_model.model.layers.23.self_attn.q_a_proj",
    "language_model.model.layers.23.self_attn.q_b_proj",
    "language_model.model.layers.22.mlp.gate",
    "language_model.model.layers.22.mlp.shared_experts.down_proj",
    "language_model.model.layers.22.mlp.shared_experts.gate_proj",
    "language_model.model.layers.22.mlp.shared_experts.up_proj",
    "language_model.model.layers.22.self_attn.kv_a_proj_with_mqa",
    "language_model.model.layers.22.self_attn.kv_b_proj",
    "language_model.model.layers.22.self_attn.o_proj",
    "language_model.model.layers.22.self_attn.q_a_proj",
    "language_model.model.layers.22.self_attn.q_b_proj"
  ],
  "provider": "auto-round"
}