{
  "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": null,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 512,
  "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"
  ],
  "linear_attn_config": {
    "head_dim": 128,
    "num_heads": 8,
    "num_kv_heads": null,
    "short_conv_kernel_size": 4
  },
  "max_position_embeddings": 4096,
  "model_type": "solar_open2",
  "moe_intermediate_size": 256,
  "n_group": 1,
  "n_routed_experts": 16,
  "n_shared_experts": 1,
  "norm_topk_prob": true,
  "num_attention_heads": 8,
  "num_experts_per_tok": 4,
  "num_hidden_layers": 12,
  "num_key_value_heads": 2,
  "pad_token_id": 2,
  "partial_rotary_factor": 1.0,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "partial_rotary_factor": 1.0,
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "routed_scaling_factor": 1.0,
  "tie_word_embeddings": false,
  "topk_group": 1,
  "transformers_version": "5.15.0.dev0",
  "use_cache": true,
  "use_gqa_gate": true,
  "use_gqa_gate_bias": false,
  "use_qk_norm": false,
  "use_rope": false,
  "vocab_size": 196608
}