{
  "H_cycles": 3,
  "L_cycles": 2,
  "architectures": [
    "GemmaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "dtype": "float32",
  "eos_token_id": 1,
  "head_dim": 256,
  "hidden_act": "gelu_pytorch_tanh",
  "hidden_size": 2048,
  "hrm_layers": 2,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 8192,
  "max_thoughts": 4,
  "merged_lm_and_talk_heads": false,
  "model_type": "gemma",
  "num_attention_heads": 8,
  "num_hidden_layers": 8,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "sliding_window": null,
  "transformers_version": "4.56.1",
  "use_cache": true,
  "use_complex_talk_head": false,
  "use_concat_talk_head": false,
  "use_shallow_talk": false,
  "use_weighted_talk_head": false,
  "vocab_size": 262152
}