{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "eos_token_id": 128001,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 32768,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 128004,
  "pretraining_tp": 1,
  "quantization_config": {
    "autoround_version": "0.6.0",
    "batch_size": 4,
    "bits": 4,
    "data_type": "int",
    "gradient_accumulate_steps": 2,
    "group_size": 128,
    "iters": 1000,
    "low_gpu_mem_usage": true,
    "nsamples": 512,
    "packing_format": "auto_round:auto_gptq",
    "quant_method": "auto-round",
    "sym": true
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 100000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.53.3",
  "use_cache": false,
  "vocab_size": 128256
}