config.json

{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "dtype": "bfloat16",
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "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": {
    "quant_method": "compressed-tensors",
    "sparsity_config": {},
    "transform_config": {
      "config_groups": {
        "u": {
          "apply": [
            {
              "ignore": [
                "lm_head"
              ],
              "inverse": false,
              "location": "weight_output",
              "targets": [
                "Linear"
              ]
            },
            {
              "ignore": [
                "lm_head"
              ],
              "inverse": true,
              "location": "output",
              "targets": [
                "Linear"
              ]
            }
          ],
          "head_dim": null,
          "precision": "torch.float64",
          "randomize": false,
          "requires_grad": false,
          "type": "hadamard"
        },
        "v": {
          "apply": [
            {
              "ignore": [
                "lm_head"
              ],
              "inverse": false,
              "location": "input",
              "targets": [
                "Linear"
              ]
            },
            {
              "ignore": [
                "lm_head"
              ],
              "inverse": true,
              "location": "weight_input",
              "targets": [
                "Linear"
              ]
            }
          ],
          "head_dim": null,
          "precision": "torch.float64",
          "randomize": false,
          "requires_grad": false,
          "type": "hadamard"
        }
      }
    },
    "version": "0.10.3.dev28+gd418aea"
  },
  "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": false,
  "transformers_version": "4.56.0.dev0",
  "use_cache": true,
  "vocab_size": 128256
}