{
  "activation_function": "silu",
  "architectures": [
    "ExaoneForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_exaone.ExaoneConfig",
    "AutoModelForCausalLM": "modeling_exaone.ExaoneForCausalLM",
    "AutoModelForSequenceClassification": "modeling_exaone.ExaoneForSequenceClassification"
  },
  "bos_token_id": 1,
  "embed_dropout": 0.0,
  "eos_token_id": 361,
  "head_dim": 80,
  "hidden_size": 2560,
  "initializer_range": 0.02,
  "intermediate_size": 7168,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 32768,
  "model_type": "exaone",
  "num_attention_heads": 32,
  "num_key_value_heads": 8,
  "num_layers": 30,
  "pad_token_id": 0,
  "quantization_config": {
    "backend": "autoawq",
    "bits": 4,
    "do_fuse": false,
    "exllama_config": null,
    "fuse_max_seq_len": null,
    "group_size": 128,
    "modules_to_fuse": null,
    "modules_to_not_convert": [
      "lm_head"
    ],
    "quant_method": "awq",
    "version": "gemm",
    "zero_point": true
  },
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 1000000,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.43.0",
  "use_cache": false,
  "vocab_size": 102400
}