{
  "architectures": [
    "ApertusForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "xielu",
  "hidden_dropout": 0.0,
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "apertus",
  "num_attention_heads": 32,
  "num_hidden_layers": 16,
  "num_key_value_heads": 8,
  "pad_token_id": 1,
  "post_norm": false,
  "qk_norm": true,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.50.0.dev0",
  "use_cache": true,
  "vocab_size": 131072
}