{
  "dim": 12288,
  "n_layers": 88,
  "head_dim": 128,
  "hidden_dim": 28672,
  "n_heads": 96,
  "n_kv_heads": 8,
  "rope_theta": 1000000.0,
  "norm_eps": 1e-05,
  "vocab_size": 131072,
  "tied_embeddings": false,
  "max_position_embeddings": 262144,
  "max_seq_len": 262144,
  "q_lora_rank": null,
  "qk_rope_head_dim": null,
  "qk_nope_head_dim": null,
  "kv_lora_rank": null,
  "v_head_dim": null,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "pack-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 32,
          "num_bits": 4,
          "observer": "mse",
          "observer_kwargs": {},
          "strategy": "group",
          "symmetric": true,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.12.3.a20251203"
  },
  "yarn": {
    "original_max_position_embeddings": 4096,
    "factor": 64,
    "apply_scale": true,
    "beta": 4,
    "alpha": 1
  }
}