params.json

{
  "dim": 5120,
  "n_layers": 40,
  "head_dim": 128,
  "hidden_dim": 32768,
  "n_heads": 32,
  "n_kv_heads": 8,
  "rope_theta": 1000000000.0,
  "norm_eps": 1e-05,
  "vocab_size": 131072,
  "quantization": {
    "config_groups": {
      "group_0": {
        "input_activations": {
          "dynamic": true,
          "num_bits": 8,
          "observer": null,
          "strategy": "token",
          "symmetric": true,
          "type": "float"
        },
        "targets": [
          "Linear"
        ],
        "weights": {
          "dynamic": false,
          "num_bits": 8,
          "observer": "minmax",
          "strategy": "tensor",
          "symmetric": true,
          "type": "float"
        }
      }
    },
    "format": "float-quantized",
    "ignore": [
      "lm_head",
      "output"
    ],
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed"
  }
}