{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "dtype": "bfloat16",
  "eos_token_id": 128001,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 16,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "quantization_config": {
    "include_input_output_embeddings": false,
    "modules_to_not_convert": null,
    "quant_method": "torchao",
    "quant_type": {
      "default": {
        "_data": {
          "activation_dtype": {
            "_data": "float8_e4m3fn",
            "_type": "torch.dtype"
          },
          "activation_value_lb": null,
          "activation_value_ub": null,
          "granularity": [
            {
              "_data": {},
              "_type": "PerTensor",
              "_version": 1
            },
            {
              "_data": {},
              "_type": "PerTensor",
              "_version": 1
            }
          ],
          "kernel_preference": {
            "_data": "AUTO",
            "_type": "KernelPreference"
          },
          "mm_config": {
            "_data": {
              "emulate": false,
              "pad_inner_dim": false,
              "use_fast_accum": true
            },
            "_type": "Float8MMConfig",
            "_version": 1
          },
          "set_inductor_config": true,
          "weight_dtype": {
            "_data": "float8_e4m3fn",
            "_type": "torch.dtype"
          }
        },
        "_type": "Float8DynamicActivationFloat8WeightConfig",
        "_version": 2
      }
    },
    "quant_type_kwargs": {},
    "untie_embedding_weights": false
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 32.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": true,
  "transformers_version": "4.56.1",
  "use_cache": true,
  "vocab_size": 128256
}