config.json

{
  "architectures": [
    "SpikeWhaleLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "config.SpikeWhaleConfig",
    "AutoModel": "model_v2.SpikeWhaleLM",
    "AutoModelForCausalLM": "model_v2.SpikeWhaleLM"
  },
  "bos_token_id": 2,
  "dtype": "float32",
  "engram_compress_dim": 32,
  "engram_gate_init_bias": -1.0,
  "engram_max_ngram": 3,
  "engram_num_heads": 2,
  "engram_table_size": 4096,
  "eos_token_id": 3,
  "hc_eps": 1e-06,
  "hc_mult": 2,
  "hc_sinkhorn_iters": 20,
  "head_dim": 64,
  "hidden_dropout": 0.0,
  "hidden_size": 640,
  "hrm_refine_dim": 128,
  "hrm_refine_steps": 1,
  "initializer_range": 0.02,
  "jepa_horizon": 1,
  "jepa_loss_weight": 0.1,
  "jepa_pred_dim": 256,
  "max_position_embeddings": 4096,
  "model_type": "spike_whale",
  "moe_aux_loss_coef": 0.01,
  "moe_intermediate_size": 2000,
  "moe_layers": [],
  "mtp_loss_weight": 0.3,
  "n_routed_experts": 6,
  "n_shared_experts": 1,
  "nope_head_dim": 48,
  "norm_topk_prob": true,
  "num_attention_heads": 10,
  "num_experts_per_tok": 2,
  "num_hash_layers": 2,
  "num_hidden_layers": 16,
  "num_key_value_heads": 1,
  "num_nextn_predict_layers": 1,
  "o_lora_rank": 128,
  "q_lora_rank": 128,
  "qk_rope_head_dim": 16,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "routed_scaling_factor": 1.0,
  "scoring_func": "sqrtsoftplus",
  "tie_word_embeddings": true,
  "transformers_version": "4.57.6",
  "use_derf": false,
  "use_engram": true,
  "use_hrm_refine": true,
  "use_hyper_connections": true,
  "use_jepa": true,
  "use_moe": false,
  "use_qk_norm": true,
  "use_value_embed": false,
  "use_xsa": true,
  "vocab_size": 16512,
  "zloss_coef": 0.0001
}