{
  "created_at": "2026-06-16T19:21:52.349847+00:00",
  "files": [
    {
      "path": "README.md",
      "size": 2567
    },
    {
      "path": "UPLOAD_MANIFEST.json",
      "size": 3606
    },
    {
      "path": "chat_template.jinja",
      "size": 7747
    },
    {
      "path": "config.json",
      "size": 5598
    },
    {
      "path": "generation_config.json",
      "size": 162
    },
    {
      "path": "model-00001-of-00005.safetensors",
      "size": 4296105224
    },
    {
      "path": "model-00002-of-00005.safetensors",
      "size": 4298580456
    },
    {
      "path": "model-00003-of-00005.safetensors",
      "size": 4298546944
    },
    {
      "path": "model-00004-of-00005.safetensors",
      "size": 4298596456
    },
    {
      "path": "model-00005-of-00005.safetensors",
      "size": 3460854912
    },
    {
      "path": "model.safetensors.index.json",
      "size": 13150295
    },
    {
      "path": "processor_config.json",
      "size": 1297
    },
    {
      "path": "quantize_config.json",
      "size": 1847
    },
    {
      "path": "tokenizer.json",
      "size": 19989343
    },
    {
      "path": "tokenizer_config.json",
      "size": 1219
    }
  ],
  "inspection": {
    "architectures": [
      "Qwen3_5MoeForConditionalGeneration"
    ],
    "artifact": "/workspace/out/nex-n2-mini/GPTQ-Pro-FOEM-4bit-g128-ns256-text-main",
    "config_model_type": "qwen3_5_moe",
    "has_mtp_tensors": false,
    "has_vision_tensors": true,
    "index_keys": 124576,
    "metadata_total_size": 20652683992,
    "metadata_total_size_matches": true,
    "quant_meta": {
      "act_group_aware": true,
      "activation_weighted_mse": true,
      "auto_forward_data_parallel": true,
      "calibration_dataset": "wikitext",
      "damp_auto_increment": 0.01,
      "damp_percent": 0.05,
      "dense_vram_strategy": "exclusive",
      "dense_vram_strategy_devices": [
        "cuda:0"
      ],
      "fallback": {
        "smooth": {
          "group_size_threshold": 128,
          "maxshrink": 0.9,
          "steps": 32,
          "type": "mse"
        },
        "strategy": "rtn",
        "threshold": "0.5%"
      },
      "foem": {
        "alpha": 0.25,
        "beta": 0.2,
        "device": "cuda:0"
      },
      "gc_mode": "interval",
      "gptaq": null,
      "hessian": {
        "chunk_bytes": null,
        "chunk_size": null,
        "staging_dtype": "float32"
      },
      "mock_quantization": false,
      "moe": {
        "routing": {
          "batch_size": 320,
          "class": "ExpertsRoutingBypass"
        }
      },
      "moe_vram_strategy": "balanced",
      "moe_vram_strategy_devices": [
        "cuda:0"
      ],
      "mse": 2.0,
      "nsamples": 256,
      "offload_to_disk": false,
      "offload_to_disk_path": null,
      "pack_impl": "cpu",
      "quantizer": [
        "gptqmodel:6.1.0-dev"
      ],
      "reference_recipe": "groxaxo/Qwen3.6-27B-GPTQ-Pro-4bit",
      "seqlen": 2048,
      "source_model": "nex-agi/Nex-N2-mini",
      "static_groups": false,
      "true_sequential": true,
      "uri": "https://github.com/modelcloud/gptqmodel",
      "wait_for_submodule_finalizers": false
    },
    "qweight_tensors": 30970,
    "referenced_shards": [
      "model-00001-of-00005.safetensors",
      "model-00002-of-00005.safetensors",
      "model-00003-of-00005.safetensors",
      "model-00004-of-00005.safetensors",
      "model-00005-of-00005.safetensors"
    ],
    "safetensors_bytes": 20652683992,
    "safetensors_count": 5,
    "unreferenced_shards": []
  },
  "repo_id": "XReyRobert/Nex-N2-mini-GPTQ-Pro"
}