{
  "model_type": "laneformer",
  "architectures": [
    "LaneformerForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_laneformer.LaneformerConfig",
    "AutoModel": "modeling_laneformer.LaneformerModel",
    "AutoModelForCausalLM": "modeling_laneformer.LaneformerForCausalLM"
  },
  "hidden_size": 3072,
  "num_hidden_layers": 15,
  "num_attention_heads": 32,
  "num_key_value_heads": 16,
  "intermediate_size": 12288,
  "max_position_embeddings": 4096,
  "max_seq_len": 4096,
  "eos_token_id": 2,
  "pad_token_id": 2,
  "vocab_size": 32000,
  "rope_theta": 10000,
  "norm_eps": 1e-05,
  "use_cache": false,
  "num_lanes": 8,
  "broadcast_delay": 2,
  "use_attention_comm": true,
  "use_mlp_comm": true,
  "use_early_comm": false,
  "lm_head_type": "vocab_parallel",
  "pre_norm_lane_agg": false,
  "replicated_rmsn_scale": true,
  "tie_word_embeddings": false,
  "sliding_window": 2048,
  "swa_layers": [
    0,
    1,
    2,
    3,
    4,
    5,
    6,
    7,
    8,
    9
  ],
  "layer_types": [
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "_attn_implementation": "sdpa",
  "dtype": "bfloat16",
  "transformers_version": "4.57.6"
}