{
  "architectures": [
    "SolarOpen2ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "first_k_dense_replace": 0,
  "gqa_interval": 3,
  "gqa_layers": [
    0,
    4,
    8,
    12,
    16,
    20,
    24,
    28,
    32,
    36,
    40,
    44
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 10240,
  "kda_allow_neg_eigval": true,
  "kda_gate_lower_bound": -5.0,
  "kda_use_full_proj": false,
  "layer_types": [
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention"
  ],
  "linear_attn_config": {
    "head_dim": 128,
    "num_heads": 64,
    "num_kv_heads": null,
    "short_conv_kernel_size": 4
  },
  "max_position_embeddings": 1048576,
  "model_type": "solar_open2",
  "moe_intermediate_size": 1280,
  "n_group": 1,
  "n_routed_experts": 184,
  "n_shared_experts": 1,
  "norm_topk_prob": true,
  "num_attention_heads": 64,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 48,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "partial_rotary_factor": 1.0,
  "quantization_config": {
    "config_groups": {
      "config_group_0": {
        "format": "nvfp4-pack-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 16,
          "num_bits": 4,
          "observer": "memoryless_minmax",
          "observer_kwargs": {},
          "scale_dtype": "torch.float8_e4m3fn",
          "strategy": "tensor_group",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        }
      }
    },
    "format": "nvfp4-pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "re:^model\\.layers\\.\\d+\\.self_attn\\..*$",
      "re:^model\\.layers\\.\\d+\\.mlp\\.shared_experts\\..*$",
      "re:^model\\.layers\\.\\d+\\.mlp\\.gate.*$",
      "model.embed_tokens",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "transform_config": {},
    "version": "0.17.1"
  },
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "partial_rotary_factor": 1.0,
    "rope_theta": 10000,
    "rope_type": "default"
  },
  "routed_scaling_factor": 1.0,
  "tie_word_embeddings": false,
  "topk_group": 1,
  "transformers_version": "5.14.1+solaropen2",
  "use_cache": true,
  "use_gqa_gate": true,
  "use_gqa_gate_bias": false,
  "use_qk_norm": false,
  "use_rope": false,
  "vocab_size": 196608
}