{
  "architectures": [
    "Gemma2ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_logit_softcapping": 50.0,
  "bos_token_id": 2,
  "cache_implementation": "hybrid",
  "eos_token_id": 1,
  "final_logit_softcapping": 30.0,
  "head_dim": 256,
  "hidden_act": "gelu_pytorch_tanh",
  "hidden_activation": "gelu_pytorch_tanh",
  "hidden_size": 2304,
  "initializer_range": 0.02,
  "intermediate_size": 9216,
  "max_position_embeddings": 8192,
  "model_type": "gemma2",
  "num_attention_heads": 8,
  "num_hidden_layers": 26,
  "num_key_value_heads": 4,
  "pad_token_id": 0,
  "quantization_config": {
    "bits": 2,
    "checkpoint_format": "gptq",
    "desc_act": true,
    "group_size": 128,
    "lm_head": false,
    "meta": {
      "damp_auto_increment": 0.01,
      "damp_percent": 0.01,
      "mse": 0.0,
      "quantizer": [
        "gptqmodel:4.0.0-dev"
      ],
      "static_groups": false,
      "true_sequential": true,
      "uri": "https://github.com/modelcloud/gptqmodel",
      "v2": false,
      "v2_alpha": 0.25
    },
    "pack_dtype": "int32",
    "quant_method": "gptq",
    "sym": true
  },
  "query_pre_attn_scalar": 256,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "sliding_window": 4096,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.52.2",
  "use_cache": true,
  "vocab_size": 256000
}