{
  "architectures": [
    "ThermoQwenForForecasting"
  ],
  "auto_map": {
    "AutoConfig": "configuration_thermo_qwen.ThermoQwenConfig",
    "AutoModel": "modeling_thermo_qwen.ThermoQwenForForecasting"
  },
  "backbone_config": {
    "architectures": [
      "Qwen3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "dtype": "bfloat16",
    "eos_token_id": 151645,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 6144,
    "layer_types": [
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 40960,
    "max_window_layers": 28,
    "model_type": "qwen3",
    "num_attention_heads": 16,
    "num_hidden_layers": 28,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000,
    "sliding_window": null,
    "tie_word_embeddings": true,
    "transformers_version": "4.57.3",
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 151936
  },
  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
  "depth_max": -25.0,
  "depth_min": -150.0,
  "horizon": 5,
  "lora_alpha": 16,
  "lora_dropout": 0.05,
  "lora_r": 8,
  "lora_target_modules": [
    "k_proj",
    "q_proj",
    "v_proj",
    "o_proj"
  ],
  "model_type": "thermo_qwen_tsf",
  "regressor_dropout": [
    0.2,
    0.1
  ],
  "regressor_hidden_sizes": [
    256,
    64
  ],
  "transformers_version": "5.8.0"
}