{
  "model_type": "solar_open2",
  "architectures": [
    "SolarOpen2ForCausalLM"
  ],
  "pad_token_id": 2,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "partial_rotary_factor": 1.0,
  "linear_attn_config": {
    "short_conv_kernel_size": 4,
    "head_dim": 128,
    "num_heads": 64,
    "num_kv_heads": null
  },
  "hidden_size": 4096,
  "num_hidden_layers": 48,
  "num_attention_heads": 64,
  "head_dim": 128,
  "num_key_value_heads": 8,
  "vocab_size": 196608,
  "intermediate_size": 10240,
  "moe_intermediate_size": 1280,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000,
  "tie_word_embeddings": false,
  "max_position_embeddings": 1048576,
  "first_k_dense_replace": 0,
  "use_rope": false,
  "gqa_interval": 3,
  "gqa_layers": [
    0,
    4,
    8,
    12,
    16,
    20,
    24,
    28,
    32,
    36,
    40,
    44
  ],
  "use_gqa_gate": true,
  "kda_use_full_proj": false,
  "kda_allow_neg_eigval": true,
  "n_routed_experts": 320,
  "n_shared_experts": 1,
  "norm_topk_prob": true,
  "routed_scaling_factor": 1.0,
  "num_experts_per_tok": 8,
  "torch_dtype": "bfloat16",
  "transformers_version": "5.5.4",
  "quantization_config": {
    "quant_method": "compressed-tensors",
    "format": "pack-quantized",
    "config_groups": {
      "group_0": {
        "targets": [
          "re:model\\.layers\\.\\d+\\.mlp\\.experts\\.\\d+\\.(gate_proj|up_proj|down_proj)"
        ],
        "weights": {
          "num_bits": 4,
          "type": "int",
          "symmetric": true,
          "strategy": "group",
          "group_size": 128,
          "dynamic": false,
          "actorder": null,
          "observer": "minmax"
        },
        "input_activations": {
          "num_bits": 8,
          "type": "float",
          "symmetric": true,
          "strategy": "token",
          "dynamic": true,
          "observer": null
        },
        "output_activations": null,
        "format": "pack-quantized"
      },
      "group_1": {
        "targets": [
          "re:model\\.layers\\.(0|4|8|12|16|20|24|28|32|36|40|44)\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)"
        ],
        "weights": {
          "num_bits": 8,
          "type": "float",
          "symmetric": true,
          "strategy": "block",
          "block_structure": [
            128,
            128
          ],
          "group_size": null,
          "dynamic": false,
          "actorder": null,
          "observer": "minmax"
        },
        "input_activations": {
          "num_bits": 8,
          "type": "float",
          "symmetric": true,
          "strategy": "group",
          "group_size": 128,
          "dynamic": true,
          "observer": null
        },
        "output_activations": null,
        "format": "float-quantized"
      }
    },
    "ignore": [
      "lm_head",
      "re:model\\.layers\\.\\d+\\.mlp\\.gate$",
      "re:model\\.layers\\.\\d+\\.mlp\\.shared_experts\\..*",
      "re:model\\.layers\\.\\d+\\.self_attn\\.g_proj",
      "re:model\\.layers\\.\\d+\\.self_attn\\.(f_a_proj|f_b_proj|g_a_proj|g_b_proj|b_proj)",
      "re:model\\.layers\\.\\d+\\.self_attn\\.(q_conv1d|k_conv1d|v_conv1d)"
    ]
  }
}