{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128009,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "quantization_config": {
    "quant_method": "compressed-tensors",
    "sparsity_config": {},
    "transform_config": {
      "config_groups": {
        "R3": {
          "apply": [
            {
              "ignore": [],
              "inverse": false,
              "location": "q_attn",
              "targets": [
                "re:.*self_attn$"
              ]
            },
            {
              "ignore": [],
              "inverse": false,
              "location": "k_cache",
              "targets": [
                "re:.*self_attn$"
              ]
            }
          ],
          "head_dim": 128,
          "precision": "torch.float64",
          "randomize": false,
          "requires_grad": false,
          "type": "hadamard"
        }
      }
    },
    "version": "0.10.3.dev28+gd418aea"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.55.0",
  "use_cache": true,
  "vocab_size": 128256
}