config.json

{
  "architectures": [
    "PMNetForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.1,
  "bos_token_id": 254,
  "dtype": "float32",
  "eos_token_id": 255,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 1024,
  "layer_types": [
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention"
  ],
  "max_position_embeddings": 40960,
  "max_window_layers": 0,
  "memory_cumsum": true,
  "memory_size": 512,
  "memory_write_period": 3,
  "model_type": "pmnet",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "num_key_value_heads": 12,
  "num_memory": 4,
  "num_memory_read_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": 128,
  "tie_word_embeddings": true,
  "transformers_version": "4.57.6",
  "use_cache": false,
  "use_sliding_window": true,
  "vocab_size": 384,
  "auto_map": {
    "AutoConfig": "configuration_pmnet.PMNetConfig",
    "AutoModel": "modeling_pmnet.PMNetModel",
    "AutoModelForCausalLM": "modeling_pmnet.PMNetForCausalLM",
    "AutoTokenizer": [
      "tokenization_pmnet.ByteTokenizer",
      null
    ]
  }
}