{
  "_name_or_path": "/models/gemma-2b",
  "architectures": [
    "GemmaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "eos_token_id": 1,
  "head_dim": 256,
  "hidden_act": "gelu",
  "hidden_activation": null,
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 16384,
  "max_position_embeddings": 8192,
  "model_type": "gemma",
  "num_attention_heads": 8,
  "num_hidden_layers": 18,
  "num_key_value_heads": 1,
  "pad_token_id": 0,
  "quantization_config": {
    "autoround_version": "0.2.0.dev",
    "bits": 4,
    "damp_percent": 0.01,
    "desc_act": false,
    "enable_minmax_tuning": true,
    "enable_quanted_input": true,
    "group_size": 128,
    "is_marlin_format": false,
    "iters": 400,
    "lr": 0.0025,
    "minmax_lr": 0.0025,
    "model_file_base_name": "model",
    "model_name_or_path": null,
    "quant_method": "gptq",
    "scale_dtype": "float16",
    "static_groups": false,
    "sym": false,
    "true_sequential": false
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "torch_dtype": "float16",
  "transformers_version": "4.40.2",
  "use_cache": true,
  "vocab_size": 256000
}