{
    "architectures": [
        "SolarOpen2ForCausalLM"
    ],
    "bos_token_id": 1,
    "eos_token_id": [
        2,
        129
    ],
    "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_size": 4096,
    "intermediate_size": 10240,
    "kda_allow_neg_eigval": true,
    "kda_use_full_proj": false,
    "linear_attn_config": {
        "short_conv_kernel_size": 4,
        "head_dim": 128,
        "num_heads": 64,
        "num_kv_heads": null
    },
    "max_position_embeddings": 1048576,
    "model_type": "solar_open2",
    "moe_intermediate_size": 1280,
    "n_routed_experts": 320,
    "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": {
        "group_size": 32,
        "bits": 4,
        "mode": "affine",
        "model.layers.0.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.24.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.26.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.28.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.29.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.30.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.31.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.32.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.33.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.34.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.35.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.36.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.37.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.38.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.39.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.40.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.41.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.42.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.43.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.44.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.45.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.46.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.47.mlp.gate": {
            "group_size": 64,
            "bits": 8
        }
    },
    "quantization_config": {
        "group_size": 32,
        "bits": 4,
        "mode": "affine",
        "model.layers.0.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.24.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.26.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.28.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.29.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.30.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.31.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.32.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.33.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.34.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.35.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.36.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.37.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.38.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.39.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.40.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.41.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.42.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.43.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.44.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.45.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.46.mlp.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.47.mlp.gate": {
            "group_size": 64,
            "bits": 8
        }
    },
    "rms_norm_eps": 1e-05,
    "rope_theta": 10000,
    "routed_scaling_factor": 1.0,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "5.5.4",
    "use_gqa_gate": true,
    "use_rope": false,
    "vocab_size": 196608
}