{
  "architectures": [
    "DwarfForCausalLM"
  ],
  "model_type": "dwarf",
  "auto_map": {
    "AutoConfig": "configuration_dwarf.DwarfConfig",
    "AutoModelForCausalLM": "modeling_dwarf.DwarfForCausalLM"
  },
  "vocab_size": 8202,
  "d_model": 320,
  "n_layers": 12,
  "n_heads": 5,
  "n_kv_heads": 1,
  "d_ff": 864,
  "max_seq_len": 2048,
  "rope_theta": 10000.0,
  "norm_eps": 1e-05,
  "head_dim": 64,
  "torch_dtype": "float32",
  "transformers_version": "4.45.0",
  "bos_token_id": 1,
  "eos_token_id": 2,
  "num_hidden_layers": 12,
  "hidden_size": 320,
  "num_attention_heads": 5,
  "num_key_value_heads": 1
}