{
  "_attn_implementation_autoset": true,
  "_name_or_path": "/tmp/models/tmp1h8l0e2_/tmpnqee64zx",
  "architectures": [
    "FalconMambaForCausalLM"
  ],
  "bos_token_id": 0,
  "conv_kernel": 4,
  "eos_token_id": 11,
  "expand": 16,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.1,
  "intermediate_size": 8192,
  "layer_norm_epsilon": 1e-05,
  "mixer_rms_eps": 1e-06,
  "model_type": "falcon_mamba",
  "num_hidden_layers": 64,
  "pad_token_id": 11,
  "quantization_config": {
    "quant_config": {
      "offload_meta": false,
      "scale_quant_params": null,
      "weight_quant_params": {
        "axis": 1,
        "channel_wise": true,
        "group_size": 64,
        "nbits": 4,
        "optimize": true,
        "round_zero": true,
        "view_as_float": false
      },
      "zero_quant_params": null
    },
    "quant_method": "hqq",
    "skip_modules": [
      "lm_head"
    ]
  },
  "rescale_prenorm_residual": false,
  "residual_in_fp32": true,
  "state_size": 16,
  "tie_word_embeddings": false,
  "time_step_floor": 0.0001,
  "time_step_init_scheme": "random",
  "time_step_max": 0.1,
  "time_step_min": 0.001,
  "time_step_rank": 256,
  "time_step_scale": 1.0,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.48.2",
  "use_bias": false,
  "use_cache": true,
  "use_conv_bias": true,
  "use_mambapy": false,
  "vocab_size": 65024
}