{
  "architectures": [
    "TBBLoopForCausalLM"
  ],
  "model_type": "tbbloop",
  "auto_map": {
    "AutoConfig": "configuration_tbbloop.TBBLoopConfig",
    "AutoModelForCausalLM": "modeling_tbbloop.TBBLoopForCausalLM"
  },
  "native": {
    "vocab_size": 4104,
    "hidden_size": 256,
    "n_layers": 3,
    "n_heads": 4,
    "head_dim": 64,
    "n_kv_heads": 2,
    "ffn_size": 560,
    "context_length": 1024,
    "rope_theta": 10000.0,
    "rms_norm_eps": 1e-05,
    "tie_embeddings": true,
    "init_std": 0.02,
    "dropout": 0.0,
    "gradient_checkpointing": false,
    "loop_unique": 4,
    "n_loops": 3,
    "loop_train_min": 2,
    "loop_train_max": 4,
    "digit_place": true,
    "digit_lo": 24,
    "digit_hi": 33,
    "place_vocab": 16,
    "embed_rank": 96
  },
  "eval_loops": 0,
  "vocab_size": 4104,
  "hidden_size": 256,
  "num_hidden_layers": 4,
  "max_position_embeddings": 1024,
  "tie_word_embeddings": true,
  "bos_token_id": 0,
  "eos_token_id": 0,
  "torch_dtype": "float32",
  "use_cache": false
}