{
  "allow_negative_eigenvalues": false,
  "architecture": "HaikuForCausalLM",
  "architectures": [
    "HaikuForCausalLM"
  ],
  "attention_dropout": 0.0,
  "attention_head_dim": 128,
  "attention_layer_type": "gated_mla",
  "bos_token_id": 0,
  "checkpoint_step": 8400,
  "eos_token_id": 1,
  "full_attention_interval": 4,
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 3840,
  "kda_lower_bound": -5.0,
  "kda_safe_gate": true,
  "layer_types": [
    "kda",
    "kda",
    "kda",
    "gated_mla",
    "kda",
    "kda",
    "kda",
    "gated_mla",
    "kda",
    "kda",
    "kda",
    "gated_mla",
    "kda",
    "kda",
    "kda",
    "gated_mla",
    "kda",
    "kda",
    "kda",
    "gated_mla",
    "kda",
    "kda",
    "kda",
    "gated_mla",
    "kda",
    "kda",
    "kda",
    "gated_mla",
    "kda",
    "kda",
    "kda",
    "gated_mla",
    "kda",
    "kda",
    "kda",
    "gated_mla"
  ],
  "linear_conv_kernel_dim": 4,
  "linear_expand_v": 1.0,
  "linear_head_dim": 128,
  "linear_layer_type": "kda",
  "linear_num_heads": 8,
  "linear_num_value_heads": 8,
  "max_position_embeddings": 32768,
  "mla_kv_lora_rank": 256,
  "mla_q_lora_rank": 512,
  "mla_qk_nope_head_dim": 128,
  "mla_v_head_dim": 128,
  "mlp_activation": "situ_glu",
  "model_family": "Haiku",
  "model_name": "Haiku-base",
  "model_type": "haiku",
  "mtp_adapter_rank": 128,
  "mtp_loss_weight": 0.2,
  "mtp_num_heads": 2,
  "num_attention_heads": 8,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "partial_rotary_factor": 0.5,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "shared_layer_indices": [],
  "situ_gate_cap": 4.0,
  "situ_up_cap": 25.0,
  "stage": "pretrain",
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "training_sequence_length": 2048,
  "transformers_version": "4.45.0",
  "unk_token_id": 3,
  "use_block_attn_res": true,
  "vocab_size": 65536,
  "weights": "ema"
}