quantization_config.json

{
  "config_groups": {
    "group_0": {
      "targets": [
        "Linear"
      ],
      "weights": {
        "num_bits": 8,
        "type": "float",
        "symmetric": true,
        "group_size": 32,
        "strategy": "group",
        "block_structure": null,
        "dynamic": false,
        "actorder": null,
        "scale_dtype": "torch.uint8",
        "zp_dtype": null,
        "observer": "memoryless_minmax",
        "observer_kwargs": {}
      },
      "input_activations": {
        "num_bits": 8,
        "type": "float",
        "symmetric": true,
        "group_size": 32,
        "strategy": "group",
        "block_structure": null,
        "dynamic": true,
        "actorder": null,
        "scale_dtype": "torch.uint8",
        "zp_dtype": null,
        "observer": null,
        "observer_kwargs": {}
      },
      "output_activations": null,
      "format": null
    }
  },
  "quant_method": "compressed-tensors",
  "kv_cache_scheme": null,
  "format": "mxfp8-quantized",
  "quantization_status": "compressed",
  "global_compression_ratio": null,
  "ignore": [
    "lm_head"
  ],
  "provider": "auto-round"
}