{
  "_attn_implementation_autoset": true,
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 100000,
  "eos_token_id": 100001,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 65536,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 30,
  "num_key_value_heads": 32,
  "pretraining_tp": 1,
  "quantization_config": {
    "bits": 4,
    "damp_percent": 0.01,
    "desc_act": false,
    "group_size": 128,
    "is_marlin_format": false,
    "model_file_base_name": "model",
    "model_name_or_path": null,
    "quant_method": "gptq",
    "static_groups": false,
    "sym": false,
    "true_sequential": true
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "beta_fast": 32,
    "beta_slow": 1,
    "factor": 16,
    "mscale": true,
    "original_max_position_embeddings": 4096,
    "rope_type": "yarn",
    "type": "yarn"
  },
  "rope_theta": 10000,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.51.3",
  "use_cache": true,
  "vocab_size": 102400
}