config.json

{
  "architectures": [
    "PositionXLNetForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 960,
  "initializer_range": 0.02,
  "intermediate_size": 2560,
  "max_position_embeddings": 256,
  "mlp_bias": false,
  "model_type": "position-xlnet",
  "num_attention_heads": 15,
  "num_hidden_layers": 32,
  "num_key_value_heads": 5,
  "num_positions": 3,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.51.3",
  "use_cache": true,
  "use_positions": [
    0,
    1,
    2
  ],
  "vocab_size": 16000,
  "auto_map": {
    "AutoConfig": "modeling_xlnet.PositionXLNetConfig",
    "AutoModelForCausalLM": "modeling_xlnet.PositionXLNetForCausalLM"
  }
}