{
  "architectures": [
    "INFLMForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_inflm.INFLMConfig",
    "AutoModelForCausalLM": "modeling_inflm.INFLMForCausalLM"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 22016,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 32768,
  "mlp_bias": false,
  "model_type": "inflm",
  "num_attention_heads": 64,
  "num_hidden_layers": 48,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "quantization_config": {
    "bits": 4,
    "checkpoint_format": "gptq",
    "damp_percent": 0.1,
    "desc_act": false,
    "group_size": 128,
    "model_file_base_name": "model",
    "model_name_or_path": null,
    "quant_method": "gptq",
    "static_groups": false,
    "sym": true,
    "true_sequential": true
  },
  "rope_scaling": null,
  "rope_theta": 500000,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "use_cache": true,
  "vocab_size": 96512
}