{
  "architectures": [
    "MambaForCausalLM"
  ],
  "bos_token_id": 1,
  "conv_kernel": 4,
  "d_model": 768,
  "eos_token_id": 2,
  "expand": 2,
  "hidden_act": "silu",
  "hidden_size": 768,
  "initializer_range": 0.1,
  "intermediate_size": 1536,
  "layer_norm_epsilon": 1e-05,
  "model_type": "mamba",
  "num_hidden_layers": 36,
  "pad_token_id": 2,
  "rescale_prenorm_residual": false,
  "residual_in_fp32": true,
  "state_size": 16,
  "time_step_floor": 0.0001,
  "time_step_init_scheme": "random",
  "time_step_max": 0.1,
  "time_step_min": 0.001,
  "time_step_rank": 48,
  "time_step_scale": 1.0,
  "torch_dtype": "float32",
  "transformers_version": "4.44.2",
  "use_bias": false,
  "use_cache": true,
  "use_conv_bias": true,
  "use_mambapy": false,
  "vocab_size": 32000
}