{
  "architectures": [
    "BarbetForCausalLM"
  ],
  "attention_dropout": 0.0,
  "attention_sink": false,
  "auto_map": {
    "AutoConfig": "configuration_barbet.BarbetConfig",
    "AutoModel": "modeling_barbet.BarbetModel",
    "AutoModelForCausalLM": "modeling_barbet.BarbetForCausalLM"
  },
  "bos_token_id": 114689,
  "dtype": "bfloat16",
  "eos_token_id": 114690,
  "global_attention_layers": [
    0,
    4,
    8,
    12,
    16,
    20,
    24
  ],
  "head_dim": 128,
  "hidden_dropout": 0.0,
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "intermediate_size": 5120,
  "mamba_d_conv": 4,
  "mamba_d_state": 64,
  "mamba_expand": 2,
  "mamba_layers": [
    3,
    7,
    11,
    15,
    19,
    23,
    27
  ],
  "max_position_embeddings": 262144,
  "model_type": "barbet",
  "mtp_enabled": false,
  "mtp_loss_weights": {
    "2": 0.2,
    "3": 0.1
  },
  "mtp_offsets": [
    2,
    3
  ],
  "num_attention_heads": 16,
  "num_hidden_layers": 28,
  "num_key_value_heads": 2,
  "pad_token_id": 114691,
  "qk_clip_alpha": 0.5,
  "qk_clip_threshold": 100.0,
  "qk_logit_clip": false,
  "qk_norm": true,
  "rms_norm_eps": 0.000001,
  "rope_parameters": null,
  "rope_theta": 10000000.0,
  "sliding_window_size": 8192,
  "tie_word_embeddings": true,
  "transformers_version": "5.12.1",
  "unk_token_id": 114688,
  "use_cache": false,
  "vocab_size": 114944
}